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

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

Neuron 666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.7279. Min Act: -0.0003

Data Index: 152994 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6736. Min Act: -0.0003

Data Index: 295893 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6397. Min Act: -0.0003

Data Index: 670821 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6551. Min Act: -0.0003

Data Index: 1337645 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6296. Min Act: -0.0003

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6117. Min Act: -0.0002

Data Index: 500097 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6265. Min Act: -0.0003

Data Index: 904611 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6067. Min Act: -0.0003

Data Index: 413299 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5881. Min Act: -0.0003

Data Index: 294754 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6256. Min Act: -0.0003

Data Index: 894612 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6262. Min Act: -0.0003

Data Index: 440812 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.6035. Min Act: -0.0003

Data Index: 1187560 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5847. Min Act: -0.0003

Data Index: 819926 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5791. Min Act: -0.0003

Data Index: 404767 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5754. Min Act: -0.0003

Data Index: 681978 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5993. Min Act: -0.0002

Data Index: 4358 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5726. Min Act: -0.0003

Data Index: 315310 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5892. Min Act: -0.0003

Data Index: 1016816 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5781. Min Act: -0.0002

Data Index: 807143 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.7279. Min Range: -0.7279

Max Act: 0.5454. Min Act: -0.0003

Data Index: 987896 (C4 (Web Text))

Max Activating Token Index: 645