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

Dataset: Open Web Text

Neuron 1709 in Layer 1

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: 2.5608. Min Range: -2.5608

Max Act: 2.5608. Min Act: -0.1700

Data Index: 3175902 (Open Web Text)

Max Activating Token Index: 835

Text #1

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.5352. Min Act: -0.1700

Data Index: 877483 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4996. Min Act: -0.1700

Data Index: 3057546 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4646. Min Act: -0.1700

Data Index: 1219731 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4341. Min Act: -0.1700

Data Index: 5497904 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4473. Min Act: -0.1700

Data Index: 7675741 (Open Web Text)

Max Activating Token Index: 786

Text #6

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4372. Min Act: -0.1700

Data Index: 431965 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4204. Min Act: -0.1700

Data Index: 6854653 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4226. Min Act: -0.1700

Data Index: 1932213 (Open Web Text)

Max Activating Token Index: 847

Text #9

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4180. Min Act: -0.1700

Data Index: 4286169 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4032. Min Act: -0.1700

Data Index: 7515638 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4120. Min Act: -0.1700

Data Index: 5496119 (Open Web Text)

Max Activating Token Index: 795

Text #12

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4130. Min Act: -0.1700

Data Index: 930722 (Open Web Text)

Max Activating Token Index: 823

Text #13

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4145. Min Act: -0.1700

Data Index: 8396469 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4219. Min Act: -0.1700

Data Index: 1651224 (Open Web Text)

Max Activating Token Index: 822

Text #15

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4075. Min Act: -0.1700

Data Index: 8164731 (Open Web Text)

Max Activating Token Index: 812

Text #16

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.4220. Min Act: -0.1700

Data Index: 375134 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.3949. Min Act: -0.1700

Data Index: 7033642 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.3969. Min Act: -0.1700

Data Index: 4056867 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 2.5608. Min Range: -2.5608

Max Act: 2.3894. Min Act: -0.1700

Data Index: 4500268 (Open Web Text)

Max Activating Token Index: 787