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

Dataset: Open Web Text

Neuron 2612 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: 3.4264. Min Range: -3.4264

Max Act: 3.4264. Min Act: -0.1700

Data Index: 4292240 (Open Web Text)

Max Activating Token Index: 898

Text #1

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.3996. Min Act: -0.1700

Data Index: 8739355 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2794. Min Act: -0.1700

Data Index: 7347095 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2535. Min Act: -0.1700

Data Index: 8745850 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2473. Min Act: -0.1700

Data Index: 8160005 (Open Web Text)

Max Activating Token Index: 567

Text #5

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2376. Min Act: -0.1700

Data Index: 6900295 (Open Web Text)

Max Activating Token Index: 290

Text #6

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2385. Min Act: -0.1700

Data Index: 3688202 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2188. Min Act: -0.1700

Data Index: 3471961 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2024. Min Act: -0.1700

Data Index: 3552105 (Open Web Text)

Max Activating Token Index: 974

Text #9

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2037. Min Act: -0.1700

Data Index: 6766247 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1998. Min Act: -0.1700

Data Index: 2470008 (Open Web Text)

Max Activating Token Index: 643

Text #11

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2144. Min Act: -0.1700

Data Index: 4699378 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1786. Min Act: -0.1700

Data Index: 1986426 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1879. Min Act: -0.1700

Data Index: 860875 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2020. Min Act: -0.1700

Data Index: 2169233 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.2053. Min Act: -0.1700

Data Index: 1768965 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1854. Min Act: -0.1700

Data Index: 5858248 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1804. Min Act: -0.1700

Data Index: 7057431 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1905. Min Act: -0.1700

Data Index: 7235998 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 3.4264. Min Range: -3.4264

Max Act: 3.1737. Min Act: -0.1700

Data Index: 4360314 (Open Web Text)

Max Activating Token Index: 671