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

Dataset: Open Web Text

Neuron 1526 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: 4.0398. Min Range: -4.0398

Max Act: 4.0398. Min Act: -0.1700

Data Index: 6404180 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.8737. Min Act: -0.1700

Data Index: 8450139 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.8355. Min Act: -0.1700

Data Index: 1062131 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7803. Min Act: -0.1700

Data Index: 2790354 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7829. Min Act: -0.1700

Data Index: 6775999 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7473. Min Act: -0.1700

Data Index: 6206539 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7739. Min Act: -0.1700

Data Index: 2052141 (Open Web Text)

Max Activating Token Index: 894

Text #7

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7552. Min Act: -0.1700

Data Index: 62454 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7836. Min Act: -0.1700

Data Index: 6430585 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7826. Min Act: -0.1700

Data Index: 8691966 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7271. Min Act: -0.1700

Data Index: 4394549 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6977. Min Act: -0.1700

Data Index: 4313164 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7205. Min Act: -0.1700

Data Index: 5729081 (Open Web Text)

Max Activating Token Index: 695

Text #13

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7214. Min Act: -0.1700

Data Index: 3675817 (Open Web Text)

Max Activating Token Index: 271

Text #14

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6610. Min Act: -0.1700

Data Index: 7075833 (Open Web Text)

Max Activating Token Index: 966

Text #15

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6834. Min Act: -0.1700

Data Index: 3147975 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.7199. Min Act: -0.1700

Data Index: 7658954 (Open Web Text)

Max Activating Token Index: 765

Text #17

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6490. Min Act: -0.1700

Data Index: 2123149 (Open Web Text)

Max Activating Token Index: 946

Text #18

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6843. Min Act: -0.1700

Data Index: 7983489 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 4.0398. Min Range: -4.0398

Max Act: 3.6835. Min Act: -0.1700

Data Index: 8224862 (Open Web Text)

Max Activating Token Index: 763