Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1844 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1346528 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0251. Min Act: -0.0006

Data Index: 793655 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1191935 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0239. Min Act: -0.0006

Data Index: 388889 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0235. Min Act: -0.0006

Data Index: 865394 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1075189 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0236. Min Act: -0.0006

Data Index: 686322 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0235. Min Act: -0.0006

Data Index: 64087 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0236. Min Act: -0.0006

Data Index: 755902 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0228. Min Act: -0.0006

Data Index: 391712 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1061951 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0227. Min Act: -0.0006

Data Index: 140876 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0228. Min Act: -0.0006

Data Index: 520607 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0006

Data Index: 374534 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0215. Min Act: -0.0006

Data Index: 502213 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1280371 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0006

Data Index: 831470 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0006

Data Index: 354880 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0006

Data Index: 63560 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0208. Min Act: -0.0006

Data Index: 444079 (C4 (Web Text))

Max Activating Token Index: 297