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

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

Neuron 1059 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: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0006

Data Index: 5368 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0247. Min Act: -0.0006

Data Index: 206601 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0006

Data Index: 751576 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0006

Data Index: 189929 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0006

Data Index: 901333 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0006

Data Index: 84141 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0216. Min Act: -0.0006

Data Index: 539926 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1212932 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0222. Min Act: -0.0006

Data Index: 63278 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0006

Data Index: 763357 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1041321 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1024998 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0199. Min Act: -0.0006

Data Index: 89927 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0200. Min Act: -0.0006

Data Index: 327100 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1178948 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0196. Min Act: -0.0006

Data Index: 343135 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1268379 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1237239 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0006

Data Index: 63976 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1337495 (C4 (Web Text))

Max Activating Token Index: 320