Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0001

Data Index: 288864 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1349. Min Act: -0.0001

Data Index: 190436 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1311. Min Act: -0.0001

Data Index: 522734 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1316. Min Act: -0.0002

Data Index: 26878 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1181. Min Act: -0.0002

Data Index: 467187 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1247. Min Act: -0.0002

Data Index: 450608 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1172. Min Act: -0.0001

Data Index: 192926 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1172040 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1268893 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1266. Min Act: -0.0002

Data Index: 73206 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1181. Min Act: -0.0002

Data Index: 203049 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1207. Min Act: -0.0002

Data Index: 691310 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1168. Min Act: -0.0002

Data Index: 769927 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1259414 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1168. Min Act: -0.0002

Data Index: 688076 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1124. Min Act: -0.0002

Data Index: 520081 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1075496 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1188. Min Act: -0.0002

Data Index: 807279 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1203459 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1067. Min Act: -0.0002

Data Index: 665986 (C4 (Web Text))

Max Activating Token Index: 31