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

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

Neuron 2025 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: 0.0204. Min Range: -0.0204

Max Act: 0.0204. Min Act: -0.0006

Data Index: 506009 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0194. Min Act: -0.0006

Data Index: 239816 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0196. Min Act: -0.0006

Data Index: 546510 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0196. Min Act: -0.0006

Data Index: 314959 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0196. Min Act: -0.0006

Data Index: 613086 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0185. Min Act: -0.0006

Data Index: 58256 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0183. Min Act: -0.0006

Data Index: 139762 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0176. Min Act: -0.0006

Data Index: 639420 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1341021 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0183. Min Act: -0.0006

Data Index: 389954 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0179. Min Act: -0.0006

Data Index: 551274 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1045392 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0170. Min Act: -0.0006

Data Index: 18360 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0175. Min Act: -0.0006

Data Index: 52417 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0162. Min Act: -0.0006

Data Index: 751626 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1030342 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0174. Min Act: -0.0006

Data Index: 306308 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0161. Min Act: -0.0006

Data Index: 126554 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0169. Min Act: -0.0006

Data Index: 407081 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1338155 (C4 (Web Text))

Max Activating Token Index: 71