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

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

Neuron 2497 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0001

Data Index: 616504 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0222. Min Act: -0.0001

Data Index: 662311 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0001

Data Index: 733395 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0217. Min Act: -0.0001

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0218. Min Act: -0.0001

Data Index: 696532 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0221. Min Act: -0.0001

Data Index: 905197 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0209. Min Act: -0.0001

Data Index: 669076 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0001

Data Index: 700850 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0001

Data Index: 235631 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1256883 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0196. Min Act: -0.0001

Data Index: 682668 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0192. Min Act: -0.0001

Data Index: 355463 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1222242 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0180. Min Act: -0.0001

Data Index: 625730 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1630984 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1014442 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0001

Data Index: 379900 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1046127 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0186. Min Act: -0.0001

Data Index: 581560 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0181. Min Act: -0.0001

Data Index: 422996 (C4 (Web Text))

Max Activating Token Index: 92