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

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

Neuron 56 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: 0.0205. Min Range: -0.0205

Max Act: 0.0205. Min Act: -0.0006

Data Index: 620191 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0199. Min Act: -0.0006

Data Index: 804590 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0184. Min Act: -0.0006

Data Index: 432590 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0184. Min Act: -0.0006

Data Index: 274317 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1265635 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1287919 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0175. Min Act: -0.0006

Data Index: 663317 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0172. Min Act: -0.0006

Data Index: 146530 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1039435 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0173. Min Act: -0.0006

Data Index: 669859 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1007072 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0164. Min Act: -0.0006

Data Index: 646313 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0170. Min Act: -0.0006

Data Index: 706314 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1048175 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0169. Min Act: -0.0006

Data Index: 83990 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1168167 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0152. Min Act: -0.0006

Data Index: 150389 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0163. Min Act: -0.0006

Data Index: 305041 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0174. Min Act: -0.0006

Data Index: 408882 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0169. Min Act: -0.0006

Data Index: 134116 (C4 (Web Text))

Max Activating Token Index: 952