Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1090 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0003

Data Index: 334305 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1378. Min Act: -0.0003

Data Index: 333856 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1253. Min Act: -0.0003

Data Index: 1049083 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1198. Min Act: -0.0003

Data Index: 163932 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1299. Min Act: -0.0003

Data Index: 231690 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1278. Min Act: -0.0003

Data Index: 536862 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1323. Min Act: -0.0003

Data Index: 848199 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1176. Min Act: -0.0003

Data Index: 277361 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1228. Min Act: -0.0003

Data Index: 305309 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1256. Min Act: -0.0003

Data Index: 1204954 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1177. Min Act: -0.0003

Data Index: 715760 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1208. Min Act: -0.0003

Data Index: 681029 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1210. Min Act: -0.0003

Data Index: 641868 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1276. Min Act: -0.0003

Data Index: 549948 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1069. Min Act: -0.0003

Data Index: 367361 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1312. Min Act: -0.0003

Data Index: 758477 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1170. Min Act: -0.0003

Data Index: 688323 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1198437 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1158. Min Act: -0.0003

Data Index: 229232 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1154. Min Act: -0.0003

Data Index: 376704 (C4 (Web Text))

Max Activating Token Index: 188