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

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

Neuron 1903 in Layer 0

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: 0.0218. Min Act: -0.0006

Data Index: 589653 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1180197 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0216. Min Act: -0.0006

Data Index: 847261 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0006

Data Index: 570190 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0219. Min Act: -0.0006

Data Index: 79041 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0218. Min Act: -0.0006

Data Index: 30512 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0214. Min Act: -0.0006

Data Index: 369471 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1093565 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0214. Min Act: -0.0006

Data Index: 736684 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0209. Min Act: -0.0006

Data Index: 893354 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0213. Min Act: -0.0006

Data Index: 22817 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0208. Min Act: -0.0006

Data Index: 507301 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0006

Data Index: 976861 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0006

Data Index: 870522 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0208. Min Act: -0.0006

Data Index: 103565 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0213. Min Act: -0.0006

Data Index: 259176 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1331423 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1224029 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0006

Data Index: 843497 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0005

Data Index: 475410 (C4 (Web Text))

Max Activating Token Index: 183