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

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

Neuron 1666 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: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1298575 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1200. Min Act: -0.0002

Data Index: 653712 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1365. Min Act: -0.0002

Data Index: 751572 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1086148 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1125468 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1253. Min Act: -0.0002

Data Index: 237412 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1123110 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1186. Min Act: -0.0002

Data Index: 94883 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1129676 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1202. Min Act: -0.0002

Data Index: 1014219 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1282281 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1027370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1222. Min Act: -0.0002

Data Index: 348763 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1024. Min Act: -0.0002

Data Index: 228125 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1256. Min Act: -0.0002

Data Index: 731041 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0906. Min Act: -0.0002

Data Index: 397291 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1195. Min Act: -0.0002

Data Index: 804108 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0988. Min Act: -0.0002

Data Index: 548330 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1144136 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1071. Min Act: -0.0002

Data Index: 126925 (C4 (Web Text))

Max Activating Token Index: 257