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

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

Neuron 1347 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0003

Data Index: 997951 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1289. Min Act: -0.0003

Data Index: 1125768 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1347. Min Act: -0.0003

Data Index: 265969 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1287. Min Act: -0.0004

Data Index: 930945 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1222. Min Act: -0.0003

Data Index: 849599 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1185. Min Act: -0.0003

Data Index: 358999 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1273. Min Act: -0.0003

Data Index: 70939 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1217. Min Act: -0.0003

Data Index: 275338 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1264. Min Act: -0.0003

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1215. Min Act: -0.0003

Data Index: 573427 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1168. Min Act: -0.0003

Data Index: 716748 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1085. Min Act: -0.0003

Data Index: 502891 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1168. Min Act: -0.0003

Data Index: 800955 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1203. Min Act: -0.0003

Data Index: 1528687 (Python Code)

Max Activating Token Index: 571

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1147. Min Act: -0.0003

Data Index: 341887 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1193. Min Act: -0.0003

Data Index: 146410 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1284873 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1141. Min Act: -0.0003

Data Index: 1015313 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1133. Min Act: -0.0003

Data Index: 846985 (C4 (Web Text))

Max Activating Token Index: 16