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

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

Neuron 1638 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0197. Min Act: -0.0002

Data Index: 586820 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1359931 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0206. Min Act: -0.0002

Data Index: 689592 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0195. Min Act: -0.0002

Data Index: 668388 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1007133 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0196. Min Act: -0.0002

Data Index: 891931 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1080517 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0170. Min Act: -0.0002

Data Index: 209627 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0180. Min Act: -0.0002

Data Index: 21297 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0178. Min Act: -0.0002

Data Index: 719726 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1430903 (Python Code)

Max Activating Token Index: 333

Text #11

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0183. Min Act: -0.0002

Data Index: 245393 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1020206 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0002

Data Index: 448320 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0157. Min Act: -0.0002

Data Index: 463035 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1216803 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0156. Min Act: -0.0002

Data Index: 221813 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0169. Min Act: -0.0002

Data Index: 688299 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1590141 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0151. Min Act: -0.0002

Data Index: 873602 (C4 (Web Text))

Max Activating Token Index: 991