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

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

Neuron 352 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: 0.9927. Min Range: -0.9927

Max Act: 0.9927. Min Act: -0.0003

Data Index: 414591 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8854. Min Act: -0.0003

Data Index: 325114 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7645. Min Act: -0.0003

Data Index: 829007 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7646. Min Act: -0.0003

Data Index: 911263 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7592. Min Act: -0.0003

Data Index: 1085276 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6859. Min Act: -0.0003

Data Index: 1065454 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6999. Min Act: -0.0003

Data Index: 1192989 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6495. Min Act: -0.0002

Data Index: 1168944 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6296. Min Act: -0.0003

Data Index: 664259 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6468. Min Act: -0.0003

Data Index: 563402 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6222. Min Act: -0.0003

Data Index: 1253864 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6428. Min Act: -0.0003

Data Index: 778534 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6358. Min Act: -0.0002

Data Index: 43317 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6329. Min Act: -0.0003

Data Index: 923866 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6077. Min Act: -0.0002

Data Index: 633469 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6264. Min Act: -0.0003

Data Index: 1287368 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6268. Min Act: -0.0003

Data Index: 74829 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6043. Min Act: -0.0003

Data Index: 569910 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6164. Min Act: -0.0003

Data Index: 1139814 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6013. Min Act: -0.0002

Data Index: 1082081 (C4 (Web Text))

Max Activating Token Index: 594