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

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

Neuron 1518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6788. Min Act: -0.0002

Data Index: 151913 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6420. Min Act: -0.0002

Data Index: 109422 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.7612. Min Act: -0.0002

Data Index: 203810 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4176. Min Act: -0.0002

Data Index: 88063 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.5634. Min Act: -0.0002

Data Index: 460191 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3212. Min Act: -0.0002

Data Index: 34102 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6189. Min Act: -0.0002

Data Index: 898277 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2114. Min Act: -0.0002

Data Index: 23214 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3988. Min Act: -0.0002

Data Index: 647477 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.0744. Min Act: -0.0002

Data Index: 590812 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.1431. Min Act: -0.0002

Data Index: 374251 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2323. Min Act: -0.0002

Data Index: 719404 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.1149. Min Act: -0.0002

Data Index: 108260 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4040. Min Act: -0.0002

Data Index: 11697 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3563. Min Act: -0.0002

Data Index: 1026275 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3104. Min Act: -0.0002

Data Index: 1282282 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2345. Min Act: -0.0002

Data Index: 805725 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2686. Min Act: -0.0002

Data Index: 733060 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9974. Min Act: -0.0002

Data Index: 645366 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4564. Min Act: -0.0002

Data Index: 221271 (C4 (Web Text))

Max Activating Token Index: 981