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

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

Neuron 3686 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: 0.1271. Min Range: -0.1271

Max Act: 0.1245. Min Act: -0.0002

Data Index: 845 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1264. Min Act: -0.0002

Data Index: 231637 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1226240 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1109. Min Act: -0.0002

Data Index: 677832 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1088861 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1246128 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1226198 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1180483 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1025. Min Act: -0.0002

Data Index: 270832 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1117. Min Act: -0.0002

Data Index: 112231 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1198. Min Act: -0.0002

Data Index: 470714 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1213421 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1171. Min Act: -0.0002

Data Index: 946617 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1116. Min Act: -0.0002

Data Index: 388836 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1199. Min Act: -0.0002

Data Index: 937335 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1109. Min Act: -0.0002

Data Index: 23151 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1070. Min Act: -0.0002

Data Index: 790731 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1230. Min Act: -0.0002

Data Index: 271136 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1128. Min Act: -0.0002

Data Index: 713009 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1097. Min Act: -0.0002

Data Index: 113322 (C4 (Web Text))

Max Activating Token Index: 324