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

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

Neuron 1888 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: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0003

Data Index: 378431 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1243. Min Act: -0.0003

Data Index: 959282 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1247. Min Act: -0.0003

Data Index: 1309938 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1236. Min Act: -0.0003

Data Index: 1210658 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1202. Min Act: -0.0003

Data Index: 632324 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1197. Min Act: -0.0003

Data Index: 43179 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1005236 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1245. Min Act: -0.0003

Data Index: 627785 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1156. Min Act: -0.0003

Data Index: 623265 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1231. Min Act: -0.0003

Data Index: 110112 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1088. Min Act: -0.0003

Data Index: 110018 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1175. Min Act: -0.0003

Data Index: 91859 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1143. Min Act: -0.0003

Data Index: 734507 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1173. Min Act: -0.0003

Data Index: 435791 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1076. Min Act: -0.0003

Data Index: 72598 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1216. Min Act: -0.0003

Data Index: 637447 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1345536 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1076549 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1201. Min Act: -0.0003

Data Index: 344054 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1234. Min Act: -0.0003

Data Index: 1021946 (C4 (Web Text))

Max Activating Token Index: 351