Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.1109. Min Act: -0.1700

Data Index: 8011015 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0796. Min Act: -0.1700

Data Index: 4159086 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9858. Min Act: -0.1700

Data Index: 7764077 (Open Web Text)

Max Activating Token Index: 809

Text #3

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9546. Min Act: -0.1700

Data Index: 6086032 (Open Web Text)

Max Activating Token Index: 952

Text #4

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0171. Min Act: -0.1700

Data Index: 762572 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9546. Min Act: -0.1700

Data Index: 5461949 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9546. Min Act: -0.1700

Data Index: 8710282 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9233. Min Act: -0.1700

Data Index: 5223195 (Open Web Text)

Max Activating Token Index: 805

Text #8

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9233. Min Act: -0.1700

Data Index: 6496404 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 4620535 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8920. Min Act: -0.1700

Data Index: 1248488 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8920. Min Act: -0.1700

Data Index: 6894739 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 8650581 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8920. Min Act: -0.1700

Data Index: 8431886 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8920. Min Act: -0.1700

Data Index: 6358951 (Open Web Text)

Max Activating Token Index: 189

Text #15

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 5129326 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8295. Min Act: -0.1700

Data Index: 991857 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 2529088 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 1112974 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8608. Min Act: -0.1700

Data Index: 7556109 (Open Web Text)

Max Activating Token Index: 310