Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2473 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0004

Data Index: 497651 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1137589 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0198. Min Act: -0.0004

Data Index: 974038 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0212. Min Act: -0.0004

Data Index: 193810 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0206. Min Act: -0.0004

Data Index: 172197 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0208. Min Act: -0.0004

Data Index: 347223 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0186. Min Act: -0.0004

Data Index: 1257652 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1037803 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0192. Min Act: -0.0004

Data Index: 267598 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1182423 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0180. Min Act: -0.0004

Data Index: 666697 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0184. Min Act: -0.0004

Data Index: 260788 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0180. Min Act: -0.0004

Data Index: 1224923 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0172. Min Act: -0.0004

Data Index: 441838 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0192. Min Act: -0.0004

Data Index: 786795 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0180. Min Act: -0.0004

Data Index: 1314311 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0186. Min Act: -0.0004

Data Index: 716657 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1075183 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0182. Min Act: -0.0004

Data Index: 697161 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1229056 (C4 (Web Text))

Max Activating Token Index: 569