Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 106 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1177493 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0219. Min Act: -0.0006

Data Index: 613772 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0216. Min Act: -0.0005

Data Index: 829066 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0006

Data Index: 162967 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0006

Data Index: 719973 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1292100 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0200. Min Act: -0.0005

Data Index: 639091 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0006

Data Index: 605949 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0006

Data Index: 83000 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0006

Data Index: 546386 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0006

Data Index: 446625 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0192. Min Act: -0.0006

Data Index: 209948 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0006

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 693102 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 898799 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 811814 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1293336 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0193. Min Act: -0.0006

Data Index: 745120 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1266623 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1264784 (C4 (Web Text))

Max Activating Token Index: 93