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

Dataset: Open Web Text

Neuron 1610 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: 5.3385. Min Range: -5.3385

Max Act: 5.3385. Min Act: -0.1700

Data Index: 2655758 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.2915. Min Act: -0.1700

Data Index: 1773327 (Open Web Text)

Max Activating Token Index: 263

Text #2

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.2914. Min Act: -0.1700

Data Index: 6952240 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.2407. Min Act: -0.1700

Data Index: 4287838 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.2498. Min Act: -0.1700

Data Index: 7996577 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0878. Min Act: -0.1700

Data Index: 2514399 (Open Web Text)

Max Activating Token Index: 683

Text #6

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.1245. Min Act: -0.1700

Data Index: 6912440 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0701. Min Act: -0.1700

Data Index: 5310905 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.1041. Min Act: -0.1700

Data Index: 4842853 (Open Web Text)

Max Activating Token Index: 148

Text #9

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0655. Min Act: -0.1700

Data Index: 6444360 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0889. Min Act: -0.1700

Data Index: 3299693 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0581. Min Act: -0.1700

Data Index: 1879331 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0653. Min Act: -0.1700

Data Index: 3461435 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.1100. Min Act: -0.1700

Data Index: 2711355 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0524. Min Act: -0.1700

Data Index: 8308773 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0563. Min Act: -0.1700

Data Index: 3917559 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 5.3385. Min Range: -5.3385

Max Act: 4.9970. Min Act: -0.1700

Data Index: 5632437 (Open Web Text)

Max Activating Token Index: 743

Text #17

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0173. Min Act: -0.1700

Data Index: 7652545 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0173. Min Act: -0.1700

Data Index: 1377407 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 5.3385. Min Range: -5.3385

Max Act: 5.0039. Min Act: -0.1700

Data Index: 936004 (Open Web Text)

Max Activating Token Index: 18