Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 4154 in Layer 32

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 6571386 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0484. Min Act: -0.1700

Data Index: 35285 (Open Web Text)

Max Activating Token Index: 235

Text #2

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 73431 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8296. Min Act: -0.1700

Data Index: 7200765 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8296. Min Act: -0.1700

Data Index: 5870567 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7671. Min Act: -0.1700

Data Index: 545699 (Open Web Text)

Max Activating Token Index: 341

Text #6

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 8069103 (Open Web Text)

Max Activating Token Index: 650

Text #7

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6734. Min Act: -0.1700

Data Index: 4552293 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6421. Min Act: -0.1700

Data Index: 340149 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6421. Min Act: -0.1700

Data Index: 1739131 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6421. Min Act: -0.1700

Data Index: 2883827 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 5958157 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 6913183 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 4144612 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 2641683 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 5389959 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.6109. Min Act: -0.1700

Data Index: 4725935 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.5796. Min Act: -0.1700

Data Index: 6070719 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.5796. Min Act: -0.1700

Data Index: 3414776 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.5796. Min Act: -0.1700

Data Index: 1245079 (Open Web Text)

Max Activating Token Index: 186