Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0247. Min Act: -0.0006

Data Index: 759979 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0006

Data Index: 74227 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0237. Min Act: -0.0006

Data Index: 97132 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0236. Min Act: -0.0006

Data Index: 707472 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0006

Data Index: 589693 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0006

Data Index: 218935 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0222. Min Act: -0.0006

Data Index: 185925 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0221. Min Act: -0.0006

Data Index: 39656 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0213. Min Act: -0.0006

Data Index: 163264 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1127958 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0006

Data Index: 453895 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0213. Min Act: -0.0006

Data Index: 91007 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0217. Min Act: -0.0006

Data Index: 738096 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1247111 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0212. Min Act: -0.0006

Data Index: 133443 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0217. Min Act: -0.0006

Data Index: 518492 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0207. Min Act: -0.0006

Data Index: 812855 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0207. Min Act: -0.0006

Data Index: 577653 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0206. Min Act: -0.0006

Data Index: 351789 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0216. Min Act: -0.0006

Data Index: 667682 (C4 (Web Text))

Max Activating Token Index: 453