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

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

Neuron 4732 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: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0002

Data Index: 160069 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0242. Min Act: -0.0002

Data Index: 199022 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0226. Min Act: -0.0002

Data Index: 300983 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 938200 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1342060 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0227. Min Act: -0.0002

Data Index: 519257 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0002

Data Index: 448769 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 560814 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0224. Min Act: -0.0002

Data Index: 711306 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0226. Min Act: -0.0002

Data Index: 912371 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1352551 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0002

Data Index: 233830 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0002

Data Index: 917193 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1114057 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1238961 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0002

Data Index: 594356 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1339313 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 944715 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 49809 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 10229 (C4 (Web Text))

Max Activating Token Index: 950