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

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

Neuron 931 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: 0.1339. Min Range: -0.1339

Max Act: 0.1306. Min Act: -0.0003

Data Index: 352983 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1339. Min Act: -0.0003

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1264. Min Act: -0.0003

Data Index: 57176 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1174. Min Act: -0.0003

Data Index: 80288 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1299. Min Act: -0.0003

Data Index: 1348323 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1235. Min Act: -0.0003

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1290. Min Act: -0.0003

Data Index: 469641 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1182. Min Act: -0.0003

Data Index: 884200 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1171. Min Act: -0.0003

Data Index: 1073660 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1211. Min Act: -0.0003

Data Index: 483819 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1302. Min Act: -0.0003

Data Index: 93535 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1201. Min Act: -0.0003

Data Index: 338528 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1245. Min Act: -0.0003

Data Index: 442321 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1191. Min Act: -0.0003

Data Index: 874329 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1137. Min Act: -0.0003

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1185. Min Act: -0.0003

Data Index: 379594 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1050. Min Act: -0.0003

Data Index: 56985 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1084. Min Act: -0.0003

Data Index: 152942 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1039. Min Act: -0.0003

Data Index: 1076 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1076. Min Act: -0.0003

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 888