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

Dataset: Open Web Text

Neuron 560 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: 3.8968. Min Range: -3.8968

Max Act: 3.8954. Min Act: -0.1700

Data Index: 4770013 (Open Web Text)

Max Activating Token Index: 636

Text #1

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8968. Min Act: -0.1700

Data Index: 2448101 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8696. Min Act: -0.1700

Data Index: 5875570 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8802. Min Act: -0.1700

Data Index: 2330197 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8504. Min Act: -0.1700

Data Index: 8237686 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8107. Min Act: -0.1700

Data Index: 6999463 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8386. Min Act: -0.1700

Data Index: 8172109 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8268. Min Act: -0.1700

Data Index: 445274 (Open Web Text)

Max Activating Token Index: 897

Text #8

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1744884 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7920. Min Act: -0.1700

Data Index: 3774121 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7698. Min Act: -0.1700

Data Index: 6875649 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8022. Min Act: -0.1700

Data Index: 2712840 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7897. Min Act: -0.1700

Data Index: 6414587 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8011. Min Act: -0.1700

Data Index: 5003449 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7947. Min Act: -0.1700

Data Index: 7343405 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7867. Min Act: -0.1700

Data Index: 113967 (Open Web Text)

Max Activating Token Index: 472

Text #16

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7665. Min Act: -0.1700

Data Index: 1932229 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7614. Min Act: -0.1700

Data Index: 7307685 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7837. Min Act: -0.1700

Data Index: 2064840 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7620. Min Act: -0.1700

Data Index: 241575 (Open Web Text)

Max Activating Token Index: 1021