Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 40 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6990. Min Act: -0.1700

Data Index: 3641643 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6826. Min Act: -0.1700

Data Index: 7732370 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6756. Min Act: -0.1700

Data Index: 3059698 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6264. Min Act: -0.1700

Data Index: 2773416 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6403. Min Act: -0.1700

Data Index: 6214443 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6304. Min Act: -0.1700

Data Index: 4410857 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6403. Min Act: -0.1700

Data Index: 1454032 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5914. Min Act: -0.1700

Data Index: 497814 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6001. Min Act: -0.1700

Data Index: 785432 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5920. Min Act: -0.1700

Data Index: 7294864 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5855. Min Act: -0.1700

Data Index: 8694827 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5910. Min Act: -0.1700

Data Index: 4275201 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.6090. Min Act: -0.1700

Data Index: 4318061 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5817. Min Act: -0.1700

Data Index: 4608246 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5797. Min Act: -0.1700

Data Index: 783320 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5707. Min Act: -0.1700

Data Index: 2046148 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5687. Min Act: -0.1700

Data Index: 1397023 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5501. Min Act: -0.1700

Data Index: 3100265 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5302. Min Act: -0.1700

Data Index: 2244751 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.6990. Min Range: -4.6990

Max Act: 4.5317. Min Act: -0.1700

Data Index: 47539 (Open Web Text)

Max Activating Token Index: 2