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

Dataset: Open Web Text

Neuron 365 in Layer 4

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: 3.8879. Min Range: -3.8879

Max Act: 3.8879. Min Act: -0.1700

Data Index: 2744233 (Open Web Text)

Max Activating Token Index: 151

Text #1

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.7191. Min Act: -0.1700

Data Index: 5561643 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.6899. Min Act: -0.1700

Data Index: 7716745 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.6539. Min Act: -0.1700

Data Index: 7573714 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.6766. Min Act: -0.1700

Data Index: 8073168 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.6172. Min Act: -0.1700

Data Index: 3557780 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5913. Min Act: -0.1700

Data Index: 5496802 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1742988 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5891. Min Act: -0.1700

Data Index: 7152220 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5578. Min Act: -0.1700

Data Index: 2886188 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5388. Min Act: -0.1700

Data Index: 3263470 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5265. Min Act: -0.1700

Data Index: 7755141 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5347. Min Act: -0.1700

Data Index: 4308149 (Open Web Text)

Max Activating Token Index: 800

Text #13

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5233. Min Act: -0.1700

Data Index: 2157612 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5352. Min Act: -0.1700

Data Index: 1222534 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5153. Min Act: -0.1700

Data Index: 3824032 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5286. Min Act: -0.1700

Data Index: 3572812 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5527. Min Act: -0.1700

Data Index: 7493512 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5174. Min Act: -0.1700

Data Index: 4012215 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.8879. Min Range: -3.8879

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1081789 (Open Web Text)

Max Activating Token Index: 525