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

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

Neuron 3474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0002

Data Index: 151581 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0295. Min Act: -0.0003

Data Index: 962029 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1253810 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0244. Min Act: -0.0003

Data Index: 848028 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1489799 (Python Code)

Max Activating Token Index: 720

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1492377 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0211. Min Act: -0.0002

Data Index: 400420 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1016565 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1624276 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0212. Min Act: -0.0002

Data Index: 410525 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1336250 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1640595 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0202. Min Act: -0.0002

Data Index: 773051 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0208. Min Act: -0.0002

Data Index: 679839 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0191. Min Act: -0.0002

Data Index: 622109 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1051733 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0199. Min Act: -0.0002

Data Index: 527499 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1479933 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0190. Min Act: -0.0002

Data Index: 774810 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1398649 (Python Code)

Max Activating Token Index: 583