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

Dataset: Open Web Text

Neuron 2368 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: 3.9805. Min Range: -3.9805

Max Act: 3.9687. Min Act: -0.1700

Data Index: 298746 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.9805. Min Act: -0.1700

Data Index: 6961833 (Open Web Text)

Max Activating Token Index: 1005

Text #2

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.9473. Min Act: -0.1700

Data Index: 5558136 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.9116. Min Act: -0.1700

Data Index: 4855869 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8826. Min Act: -0.1700

Data Index: 8771105 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8692. Min Act: -0.1700

Data Index: 4982686 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8948. Min Act: -0.1700

Data Index: 357975 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.9052. Min Act: -0.1700

Data Index: 6061609 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8530. Min Act: -0.1700

Data Index: 6739668 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8425. Min Act: -0.1700

Data Index: 183020 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8493. Min Act: -0.1700

Data Index: 7253838 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8617. Min Act: -0.1700

Data Index: 1877155 (Open Web Text)

Max Activating Token Index: 353

Text #12

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8411. Min Act: -0.1700

Data Index: 3513182 (Open Web Text)

Max Activating Token Index: 996

Text #13

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8503. Min Act: -0.1700

Data Index: 3207107 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8505. Min Act: -0.1700

Data Index: 1895358 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8748. Min Act: -0.1700

Data Index: 2241941 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8247. Min Act: -0.1700

Data Index: 1195792 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8173. Min Act: -0.1700

Data Index: 4629126 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8077. Min Act: -0.1700

Data Index: 5512166 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.9805. Min Range: -3.9805

Max Act: 3.8158. Min Act: -0.1700

Data Index: 1857862 (Open Web Text)

Max Activating Token Index: 954