Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 384 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1342572 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1326. Min Act: -0.0001

Data Index: 183895 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1286. Min Act: -0.0002

Data Index: 796908 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1317. Min Act: -0.0002

Data Index: 4887 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1274. Min Act: -0.0001

Data Index: 803492 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1199. Min Act: -0.0001

Data Index: 258023 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1193. Min Act: -0.0001

Data Index: 152676 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1230. Min Act: -0.0001

Data Index: 604390 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1175. Min Act: -0.0002

Data Index: 572705 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1164. Min Act: -0.0002

Data Index: 77773 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1170857 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1185. Min Act: -0.0001

Data Index: 115221 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1065258 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1134. Min Act: -0.0001

Data Index: 607238 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1044284 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1087. Min Act: -0.0002

Data Index: 642270 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1053790 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1170. Min Act: -0.0001

Data Index: 197751 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1223525 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1035. Min Act: -0.0002

Data Index: 951574 (C4 (Web Text))

Max Activating Token Index: 849