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

Dataset: Open Web Text

Neuron 2157 in Layer 5

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: 4.3437. Min Range: -4.3437

Max Act: 4.3437. Min Act: -0.1700

Data Index: 4567625 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.2580. Min Act: -0.1700

Data Index: 6208489 (Open Web Text)

Max Activating Token Index: 81

Text #2

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.2675. Min Act: -0.1700

Data Index: 6312770 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.2962. Min Act: -0.1700

Data Index: 1662859 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.2102. Min Act: -0.1700

Data Index: 4366175 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1959. Min Act: -0.1700

Data Index: 5752104 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.2231. Min Act: -0.1700

Data Index: 2511593 (Open Web Text)

Max Activating Token Index: 194

Text #7

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1720. Min Act: -0.1700

Data Index: 5451289 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1813. Min Act: -0.1700

Data Index: 1507393 (Open Web Text)

Max Activating Token Index: 854

Text #9

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1391. Min Act: -0.1700

Data Index: 5383114 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1431. Min Act: -0.1700

Data Index: 4030379 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1787. Min Act: -0.1700

Data Index: 3538428 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1573. Min Act: -0.1700

Data Index: 7316510 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1407. Min Act: -0.1700

Data Index: 8511027 (Open Web Text)

Max Activating Token Index: 185

Text #14

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1067. Min Act: -0.1700

Data Index: 3802578 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1435. Min Act: -0.1700

Data Index: 3942418 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1219. Min Act: -0.1700

Data Index: 6187901 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1444. Min Act: -0.1700

Data Index: 7511676 (Open Web Text)

Max Activating Token Index: 445

Text #18

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.0904. Min Act: -0.1700

Data Index: 5199115 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 4.3437. Min Range: -4.3437

Max Act: 4.1250. Min Act: -0.1700

Data Index: 7589524 (Open Web Text)

Max Activating Token Index: 424