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

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

Neuron 351 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: 0.0250. Min Range: -0.0250

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1009454 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1128405 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0241. Min Act: -0.0006

Data Index: 12024 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0223. Min Act: -0.0006

Data Index: 442715 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 968076 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 230315 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0216. Min Act: -0.0006

Data Index: 576136 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0221. Min Act: -0.0006

Data Index: 387733 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1315067 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0218. Min Act: -0.0006

Data Index: 611694 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0208. Min Act: -0.0006

Data Index: 451929 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1049146 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0199. Min Act: -0.0006

Data Index: 46829 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1055080 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0208. Min Act: -0.0006

Data Index: 454152 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1217169 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1087297 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0203. Min Act: -0.0006

Data Index: 976225 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0006

Data Index: 521926 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1114227 (C4 (Web Text))

Max Activating Token Index: 801