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

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

Neuron 1559 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1612860 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0211. Min Act: -0.0005

Data Index: 901126 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0192. Min Act: -0.0005

Data Index: 619774 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1304131 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0193. Min Act: -0.0005

Data Index: 920685 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0184. Min Act: -0.0005

Data Index: 1246054 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0187. Min Act: -0.0005

Data Index: 227969 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0187. Min Act: -0.0006

Data Index: 147990 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0182. Min Act: -0.0006

Data Index: 505208 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0177. Min Act: -0.0005

Data Index: 845436 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0173. Min Act: -0.0005

Data Index: 1437924 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0176. Min Act: -0.0005

Data Index: 841295 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0180. Min Act: -0.0005

Data Index: 889118 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0180. Min Act: -0.0005

Data Index: 936048 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0178. Min Act: -0.0005

Data Index: 111925 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0174. Min Act: -0.0005

Data Index: 517863 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0177. Min Act: -0.0005

Data Index: 365100 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0177. Min Act: -0.0006

Data Index: 64294 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0173. Min Act: -0.0005

Data Index: 578138 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0176. Min Act: -0.0005

Data Index: 854740 (C4 (Web Text))

Max Activating Token Index: 401