Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0282. Min Act: -0.0003

Data Index: 155373 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0268. Min Act: -0.0003

Data Index: 551479 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0003

Data Index: 201295 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0291. Min Act: -0.0003

Data Index: 87286 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0297. Min Act: -0.0003

Data Index: 272880 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0263. Min Act: -0.0003

Data Index: 709330 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1215030 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0260. Min Act: -0.0003

Data Index: 595241 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1120922 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1235003 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1201839 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0244. Min Act: -0.0003

Data Index: 618865 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0250. Min Act: -0.0002

Data Index: 940551 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0243. Min Act: -0.0003

Data Index: 864877 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0223. Min Act: -0.0003

Data Index: 205338 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0227. Min Act: -0.0003

Data Index: 486976 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0231. Min Act: -0.0003

Data Index: 469113 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1465845 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0219. Min Act: -0.0003

Data Index: 18291 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0240. Min Act: -0.0003

Data Index: 636412 (C4 (Web Text))

Max Activating Token Index: 255