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

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

Neuron 4773 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: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0002

Data Index: 136851 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1098391 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1200747 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0002

Data Index: 373009 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0182. Min Act: -0.0002

Data Index: 312061 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1311948 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0190. Min Act: -0.0002

Data Index: 495112 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1016429 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1190428 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0002

Data Index: 911869 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1268528 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0185. Min Act: -0.0002

Data Index: 724911 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0177. Min Act: -0.0002

Data Index: 259713 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1343499 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1131052 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0178. Min Act: -0.0002

Data Index: 141814 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1023432 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0169. Min Act: -0.0002

Data Index: 254708 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0159. Min Act: -0.0002

Data Index: 51619 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0176. Min Act: -0.0002

Data Index: 477614 (C4 (Web Text))

Max Activating Token Index: 698