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

Dataset: Open Web Text

Neuron 1172 in Layer 1

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: 4.7465. Min Range: -4.7465

Max Act: 4.7455. Min Act: -0.1700

Data Index: 5923271 (Open Web Text)

Max Activating Token Index: 260

Text #1

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.7465. Min Act: -0.1700

Data Index: 476225 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.7072. Min Act: -0.1700

Data Index: 2211940 (Open Web Text)

Max Activating Token Index: 105

Text #3

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6795. Min Act: -0.1700

Data Index: 6174799 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6792. Min Act: -0.1700

Data Index: 6533281 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6297. Min Act: -0.1700

Data Index: 5620731 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6512. Min Act: -0.1700

Data Index: 8603823 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6217. Min Act: -0.1700

Data Index: 4379653 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6306. Min Act: -0.1700

Data Index: 4249943 (Open Web Text)

Max Activating Token Index: 469

Text #9

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6282. Min Act: -0.1700

Data Index: 953347 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6531. Min Act: -0.1700

Data Index: 3629055 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6183. Min Act: -0.1700

Data Index: 1055842 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.5912. Min Act: -0.1700

Data Index: 1377428 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.5934. Min Act: -0.1700

Data Index: 1292005 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.5824. Min Act: -0.1700

Data Index: 4237822 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6062. Min Act: -0.1700

Data Index: 3842424 (Open Web Text)

Max Activating Token Index: 246

Text #16

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.5833. Min Act: -0.1700

Data Index: 3816861 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6075. Min Act: -0.1700

Data Index: 3572866 (Open Web Text)

Max Activating Token Index: 167

Text #18

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.6025. Min Act: -0.1700

Data Index: 494936 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 4.7465. Min Range: -4.7465

Max Act: 4.5899. Min Act: -0.1700

Data Index: 3336834 (Open Web Text)

Max Activating Token Index: 10