Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1553 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2887. Min Act: -0.0001

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2683. Min Act: -0.0002

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2767. Min Act: -0.0002

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2522. Min Act: -0.0002

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2539. Min Act: -0.0002

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2270. Min Act: -0.0002

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2291. Min Act: -0.0002

Data Index: 78349 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2456. Min Act: -0.0002

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2230. Min Act: -0.0002

Data Index: 752725 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2281. Min Act: -0.0002

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2108. Min Act: -0.0002

Data Index: 661718 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2008. Min Act: -0.0002

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2265. Min Act: -0.0002

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2266. Min Act: -0.0002

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2164. Min Act: -0.0002

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2158. Min Act: -0.0002

Data Index: 50098 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2149. Min Act: -0.0002

Data Index: 714623 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2188. Min Act: -0.0002

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1805. Min Act: -0.0002

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2247. Min Act: -0.0002

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 361