Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2008 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1340623 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0307. Min Act: -0.0002

Data Index: 278752 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0219. Min Act: -0.0002

Data Index: 47396 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0204. Min Act: -0.0003

Data Index: 44882 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1329169 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1439782 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1091019 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0200. Min Act: -0.0003

Data Index: 465234 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1539503 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0189. Min Act: -0.0002

Data Index: 661978 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0168. Min Act: -0.0003

Data Index: 378636 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0174. Min Act: -0.0003

Data Index: 310732 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1446197 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0187. Min Act: -0.0003

Data Index: 588977 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1633506 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1378463 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0172. Min Act: -0.0003

Data Index: 152486 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0175. Min Act: -0.0003

Data Index: 644460 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1376730 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1038388 (C4 (Web Text))

Max Activating Token Index: 298