Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 897586 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1045. Min Act: -0.0002

Data Index: 271439 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1080430 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1014. Min Act: -0.0001

Data Index: 302871 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0911. Min Act: -0.0001

Data Index: 429933 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1046. Min Act: -0.0002

Data Index: 551787 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0895. Min Act: -0.0002

Data Index: 933107 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1038. Min Act: -0.0001

Data Index: 47524 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0982. Min Act: -0.0001

Data Index: 314243 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1184783 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0936. Min Act: -0.0002

Data Index: 61490 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1009. Min Act: -0.0002

Data Index: 408838 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0958. Min Act: -0.0002

Data Index: 877909 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1034. Min Act: -0.0001

Data Index: 261739 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1000914 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1059. Min Act: -0.0002

Data Index: 140868 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0974. Min Act: -0.0002

Data Index: 820493 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0931. Min Act: -0.0001

Data Index: 16701 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1243407 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0946. Min Act: -0.0001

Data Index: 475105 (C4 (Web Text))

Max Activating Token Index: 227