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

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

Neuron 1695 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: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0003

Data Index: 656911 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1006915 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0249. Min Act: -0.0003

Data Index: 521522 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0208. Min Act: -0.0003

Data Index: 54897 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0211. Min Act: -0.0003

Data Index: 28108 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0195. Min Act: -0.0003

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0199. Min Act: -0.0003

Data Index: 857140 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0199. Min Act: -0.0003

Data Index: 511163 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0193. Min Act: -0.0003

Data Index: 190116 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0192. Min Act: -0.0003

Data Index: 503223 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0181. Min Act: -0.0003

Data Index: 532498 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0181. Min Act: -0.0003

Data Index: 30697 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0182. Min Act: -0.0003

Data Index: 753958 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0175. Min Act: -0.0003

Data Index: 148592 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0172. Min Act: -0.0003

Data Index: 219858 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0171. Min Act: -0.0003

Data Index: 473040 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0172. Min Act: -0.0003

Data Index: 155716 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1161889 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0177. Min Act: -0.0003

Data Index: 508416 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1143443 (C4 (Web Text))

Max Activating Token Index: 340