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

Dataset: Open Web Text

Neuron 2765 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: 1.6872. Min Range: -1.6872

Max Act: 1.6872. Min Act: -0.1664

Data Index: 8420515 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6800. Min Act: -0.1691

Data Index: 2884523 (Open Web Text)

Max Activating Token Index: 814

Text #2

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6772. Min Act: -0.1697

Data Index: 3680741 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6614. Min Act: -0.1699

Data Index: 4256662 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6328. Min Act: -0.1688

Data Index: 6834225 (Open Web Text)

Max Activating Token Index: 785

Text #5

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6222. Min Act: -0.1699

Data Index: 5492984 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6278. Min Act: -0.1696

Data Index: 8745400 (Open Web Text)

Max Activating Token Index: 619

Text #7

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6241. Min Act: -0.1700

Data Index: 6600315 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6174. Min Act: -0.1700

Data Index: 1948688 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6245. Min Act: -0.1676

Data Index: 2987945 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6144. Min Act: -0.1689

Data Index: 815484 (Open Web Text)

Max Activating Token Index: 928

Text #11

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6096. Min Act: -0.1613

Data Index: 7608769 (Open Web Text)

Max Activating Token Index: 329

Text #12

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.5921. Min Act: -0.1700

Data Index: 1129285 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.5895. Min Act: -0.1635

Data Index: 3368158 (Open Web Text)

Max Activating Token Index: 841

Text #14

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6019. Min Act: -0.1700

Data Index: 2403225 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6001. Min Act: -0.1700

Data Index: 983997 (Open Web Text)

Max Activating Token Index: 722

Text #16

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6078. Min Act: -0.1688

Data Index: 2286834 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.5915. Min Act: -0.1699

Data Index: 5297063 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.5797. Min Act: -0.1700

Data Index: 7848938 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.5884. Min Act: -0.1700

Data Index: 4715057 (Open Web Text)

Max Activating Token Index: 331