Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1411329 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0273. Min Act: -0.0003

Data Index: 893986 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0243. Min Act: -0.0003

Data Index: 821041 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1471299 (Python Code)

Max Activating Token Index: 435

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0251. Min Act: -0.0003

Data Index: 840013 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0246. Min Act: -0.0003

Data Index: 203403 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1429109 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0265. Min Act: -0.0003

Data Index: 907173 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1003734 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0244. Min Act: -0.0003

Data Index: 711066 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0239. Min Act: -0.0003

Data Index: 935173 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1069528 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0244. Min Act: -0.0003

Data Index: 688450 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1082340 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0241. Min Act: -0.0002

Data Index: 687238 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1238124 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1294663 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1639897 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0236. Min Act: -0.0003

Data Index: 868299 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0231. Min Act: -0.0003

Data Index: 286621 (C4 (Web Text))

Max Activating Token Index: 806