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

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

Neuron 43 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0004

Data Index: 1260281 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0234. Min Act: -0.0004

Data Index: 714603 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0221. Min Act: -0.0004

Data Index: 933275 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0221. Min Act: -0.0005

Data Index: 1098197 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0212. Min Act: -0.0005

Data Index: 169346 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1245058 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0216. Min Act: -0.0004

Data Index: 613630 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0206. Min Act: -0.0005

Data Index: 745648 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0210. Min Act: -0.0004

Data Index: 480997 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0207. Min Act: -0.0004

Data Index: 668413 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0203. Min Act: -0.0004

Data Index: 515202 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0205. Min Act: -0.0005

Data Index: 993740 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0204. Min Act: -0.0005

Data Index: 1243199 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0204. Min Act: -0.0004

Data Index: 608051 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0202. Min Act: -0.0005

Data Index: 954855 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0197. Min Act: -0.0005

Data Index: 495520 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1183339 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0200. Min Act: -0.0005

Data Index: 536160 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0004

Data Index: 923365 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0197. Min Act: -0.0004

Data Index: 1127722 (C4 (Web Text))

Max Activating Token Index: 818