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

Dataset: Open Web Text

Neuron 796 in Layer 6

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: 3.3274. Min Range: -3.3274

Max Act: 3.3274. Min Act: -0.1700

Data Index: 4590515 (Open Web Text)

Max Activating Token Index: 251

Text #1

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2435. Min Act: -0.1700

Data Index: 6517436 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1899. Min Act: -0.1700

Data Index: 4841742 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1625. Min Act: -0.1700

Data Index: 135123 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1389. Min Act: -0.1700

Data Index: 6132891 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1220. Min Act: -0.1700

Data Index: 946493 (Open Web Text)

Max Activating Token Index: 470

Text #6

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1184. Min Act: -0.1700

Data Index: 8132250 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1177. Min Act: -0.1700

Data Index: 7504041 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1073. Min Act: -0.1700

Data Index: 8720860 (Open Web Text)

Max Activating Token Index: 168

Text #9

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1071. Min Act: -0.1700

Data Index: 3161292 (Open Web Text)

Max Activating Token Index: 954

Text #10

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1125. Min Act: -0.1700

Data Index: 6062402 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0816. Min Act: -0.1700

Data Index: 7641616 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0941. Min Act: -0.1700

Data Index: 5390495 (Open Web Text)

Max Activating Token Index: 506

Text #13

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0763. Min Act: -0.1700

Data Index: 3872290 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0527. Min Act: -0.1700

Data Index: 4064696 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0826. Min Act: -0.1700

Data Index: 2708348 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0684. Min Act: -0.1700

Data Index: 6824253 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0695. Min Act: -0.1700

Data Index: 7971786 (Open Web Text)

Max Activating Token Index: 418

Text #18

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0772. Min Act: -0.1700

Data Index: 3822817 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.0862. Min Act: -0.1700

Data Index: 6673150 (Open Web Text)

Max Activating Token Index: 701