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

Dataset: Open Web Text

Neuron 629 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: 3.8200. Min Range: -3.8200

Max Act: 3.8200. Min Act: -0.1700

Data Index: 4329745 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7611. Min Act: -0.1700

Data Index: 5920277 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7468. Min Act: -0.1700

Data Index: 8290971 (Open Web Text)

Max Activating Token Index: 860

Text #3

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7346. Min Act: -0.1700

Data Index: 1778528 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.7321. Min Act: -0.1700

Data Index: 3567037 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6689. Min Act: -0.1700

Data Index: 832543 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6812. Min Act: -0.1700

Data Index: 3834306 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6501. Min Act: -0.1700

Data Index: 2928272 (Open Web Text)

Max Activating Token Index: 780

Text #8

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6630. Min Act: -0.1700

Data Index: 6770770 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6429. Min Act: -0.1700

Data Index: 2869192 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6633. Min Act: -0.1700

Data Index: 4126905 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6153. Min Act: -0.1700

Data Index: 8415139 (Open Web Text)

Max Activating Token Index: 579

Text #12

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6460. Min Act: -0.1700

Data Index: 5160653 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6581. Min Act: -0.1700

Data Index: 1588332 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6461. Min Act: -0.1700

Data Index: 1656943 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6262. Min Act: -0.1700

Data Index: 1668566 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6173. Min Act: -0.1700

Data Index: 5048555 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.6105. Min Act: -0.1700

Data Index: 1495371 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.5991. Min Act: -0.1700

Data Index: 7016998 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 3.8200. Min Range: -3.8200

Max Act: 3.5877. Min Act: -0.1700

Data Index: 4533786 (Open Web Text)

Max Activating Token Index: 488