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

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

Neuron 567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0003

Data Index: 886115 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1264. Min Act: -0.0003

Data Index: 328937 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1250. Min Act: -0.0003

Data Index: 14172 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1293. Min Act: -0.0003

Data Index: 1247164 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1229. Min Act: -0.0003

Data Index: 843790 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1266. Min Act: -0.0003

Data Index: 828994 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1177. Min Act: -0.0003

Data Index: 216824 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1253. Min Act: -0.0003

Data Index: 1032459 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1237. Min Act: -0.0003

Data Index: 549996 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1233. Min Act: -0.0002

Data Index: 517343 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1218. Min Act: -0.0003

Data Index: 1057221 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1152. Min Act: -0.0003

Data Index: 1104315 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1195. Min Act: -0.0003

Data Index: 412553 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1194. Min Act: -0.0003

Data Index: 632335 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1192. Min Act: -0.0003

Data Index: 701648 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1202. Min Act: -0.0002

Data Index: 601845 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1145. Min Act: -0.0003

Data Index: 91194 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1183. Min Act: -0.0003

Data Index: 602177 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1178. Min Act: -0.0003

Data Index: 693481 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1174. Min Act: -0.0003

Data Index: 405486 (C4 (Web Text))

Max Activating Token Index: 36