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

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

Neuron 720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1248041 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0256. Min Act: -0.0002

Data Index: 923768 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0231. Min Act: -0.0002

Data Index: 981500 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1160467 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0225. Min Act: -0.0002

Data Index: 804178 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0221. Min Act: -0.0002

Data Index: 163087 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0219. Min Act: -0.0002

Data Index: 309863 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0218. Min Act: -0.0002

Data Index: 288854 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1233327 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0213. Min Act: -0.0002

Data Index: 534563 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0210. Min Act: -0.0002

Data Index: 124641 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1080934 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1048700 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1238397 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1143227 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1281126 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0205. Min Act: -0.0002

Data Index: 349489 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1343657 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1313937 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0197. Min Act: -0.0002

Data Index: 198263 (C4 (Web Text))

Max Activating Token Index: 1012