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

Dataset: Open Web Text

Neuron 301 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: 3.9550. Min Range: -3.9550

Max Act: 3.9550. Min Act: -0.1700

Data Index: 6340198 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8465. Min Act: -0.1700

Data Index: 3622959 (Open Web Text)

Max Activating Token Index: 376

Text #2

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8607. Min Act: -0.1700

Data Index: 7736545 (Open Web Text)

Max Activating Token Index: 273

Text #3

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8286. Min Act: -0.1700

Data Index: 5753333 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8223. Min Act: -0.1700

Data Index: 5803495 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8131. Min Act: -0.1700

Data Index: 3835816 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8426. Min Act: -0.1700

Data Index: 278749 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7951. Min Act: -0.1700

Data Index: 2644500 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8087. Min Act: -0.1700

Data Index: 4624654 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7575. Min Act: -0.1700

Data Index: 2529153 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7496. Min Act: -0.1700

Data Index: 1945117 (Open Web Text)

Max Activating Token Index: 669

Text #11

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7282. Min Act: -0.1700

Data Index: 2688761 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7420. Min Act: -0.1700

Data Index: 3406283 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7178. Min Act: -0.1700

Data Index: 732473 (Open Web Text)

Max Activating Token Index: 983

Text #14

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7504. Min Act: -0.1700

Data Index: 6455298 (Open Web Text)

Max Activating Token Index: 157

Text #15

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7241. Min Act: -0.1700

Data Index: 950597 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7172. Min Act: -0.1700

Data Index: 2051199 (Open Web Text)

Max Activating Token Index: 442

Text #17

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.6681. Min Act: -0.1700

Data Index: 132287 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.6830. Min Act: -0.1700

Data Index: 3376249 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.6898. Min Act: -0.1700

Data Index: 5079241 (Open Web Text)

Max Activating Token Index: 69