Using visualize_activation on MNIST

MNIST_brain_vis.py

import numpy as np
from matplotlib import pyplot as plt
plt.rcParams['figure.figsize'] = (18, 6)
import keras

from vis.utils import utils
from vis.utils.vggnet import VGG16
from vis.visualization import visualize_activation, visualize_cam

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential, Model
from keras.layers import Dense, Dropout, Flatten, Activation, Input
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 2

# input image dimensions
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

model.save('mnist_model.h5')
model = keras.models.load_model('mnist_model.h5')
last_layer = model.layers[-1]
model.summary()

last_layer_weights = last_layer.get_weights()

model.layers.pop()
model.layers[-1].outbound_nodes = []
model.outputs = [model.layers[-1].output]
model.summary()

model.add(Dense(num_classes, activation='linear'))
model.summary()

model.layers[-1].set_weights(last_layer_weights)
layer_idx = 7
images = []
img = visualize_activation(model, layer_idx, filter_indices=[7], max_iter=1000, tv_weight=1., lp_norm_weight=0.)
#images.append(img)

#stitched = utils.stitch_images(images)
#plt.axis('off')
#plt.figure(figsize = (16, 10))
#plt.imshow(stitched)
plt.imshow(img[:, :, 0])

I added notebooks for MNIST in examples/ using your network architecture. Hope that clarifies how to debug such issues.
Feel free to reopen if you have more questions.