Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4975 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1065703 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8560. Min Act: -0.0000

Data Index: 129637 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8434. Min Act: -0.0000

Data Index: 352682 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8189. Min Act: -0.0000

Data Index: 998895 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6168. Min Act: -0.0000

Data Index: 93306 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6627. Min Act: -0.0000

Data Index: 990105 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5924. Min Act: -0.0000

Data Index: 474438 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6124. Min Act: -0.0000

Data Index: 876492 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6260. Min Act: -0.0000

Data Index: 194814 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1312234 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5035. Min Act: -0.0000

Data Index: 869931 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1059971 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.4906. Min Act: -0.0000

Data Index: 983192 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5711. Min Act: -0.0000

Data Index: 176336 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5844. Min Act: -0.0000

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5803. Min Act: -0.0000

Data Index: 337113 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1190447 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6062. Min Act: -0.0000

Data Index: 1279071 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1332337 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.5558. Min Act: -0.0000

Data Index: 107569 (C4 (Web Text))

Max Activating Token Index: 579