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

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

Neuron 259 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0239. Min Act: -0.0006

Data Index: 565300 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0243. Min Act: -0.0006

Data Index: 923295 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1002432 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0227. Min Act: -0.0006

Data Index: 687684 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0233. Min Act: -0.0006

Data Index: 739897 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0228. Min Act: -0.0007

Data Index: 320527 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0227. Min Act: -0.0006

Data Index: 777155 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1104837 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0216. Min Act: -0.0006

Data Index: 196817 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1261930 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1183404 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1304562 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1148020 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1026598 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0215. Min Act: -0.0006

Data Index: 818977 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0210. Min Act: -0.0006

Data Index: 275973 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0214. Min Act: -0.0006

Data Index: 781754 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0215. Min Act: -0.0006

Data Index: 513994 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0208. Min Act: -0.0006

Data Index: 909947 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0213. Min Act: -0.0006

Data Index: 663847 (C4 (Web Text))

Max Activating Token Index: 10