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

Dataset: Open Web Text

Neuron 785 in Layer 3

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: 3.6574. Min Range: -3.6574

Max Act: 3.6574. Min Act: -0.1700

Data Index: 2400524 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5086. Min Act: -0.1700

Data Index: 1051980 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4194. Min Act: -0.1700

Data Index: 3346367 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3467. Min Act: -0.1700

Data Index: 7911560 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3461. Min Act: -0.1700

Data Index: 3976397 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3303. Min Act: -0.1700

Data Index: 6743320 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3196. Min Act: -0.1700

Data Index: 6915802 (Open Web Text)

Max Activating Token Index: 434

Text #7

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3381. Min Act: -0.1700

Data Index: 6886861 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3237. Min Act: -0.1700

Data Index: 6222917 (Open Web Text)

Max Activating Token Index: 997

Text #9

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.3207. Min Act: -0.1700

Data Index: 588024 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2856. Min Act: -0.1700

Data Index: 316951 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2523. Min Act: -0.1700

Data Index: 8747947 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2779. Min Act: -0.1700

Data Index: 7759992 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2666. Min Act: -0.1700

Data Index: 2666335 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2812. Min Act: -0.1700

Data Index: 4277058 (Open Web Text)

Max Activating Token Index: 354

Text #15

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2848. Min Act: -0.1700

Data Index: 4228835 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2511. Min Act: -0.1700

Data Index: 940143 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2418. Min Act: -0.1700

Data Index: 1432171 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2259. Min Act: -0.1700

Data Index: 6985983 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.2318. Min Act: -0.1700

Data Index: 5056374 (Open Web Text)

Max Activating Token Index: 443