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

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

Neuron 4341 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0002

Data Index: 878927 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0219. Min Act: -0.0002

Data Index: 178264 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0220. Min Act: -0.0002

Data Index: 689576 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0215. Min Act: -0.0002

Data Index: 469853 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0211. Min Act: -0.0002

Data Index: 149926 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1053982 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1093734 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 287958 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1097072 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0002

Data Index: 94497 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0206. Min Act: -0.0002

Data Index: 551934 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0205. Min Act: -0.0002

Data Index: 454973 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1117075 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 913622 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1048370 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1349769 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 509019 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1336893 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1079196 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0198. Min Act: -0.0002

Data Index: 451772 (C4 (Web Text))

Max Activating Token Index: 95