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

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

Neuron 4400 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: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0002

Data Index: 771645 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0216. Min Act: -0.0002

Data Index: 912378 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1241282 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0207. Min Act: -0.0002

Data Index: 439239 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0207. Min Act: -0.0002

Data Index: 641255 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1320568 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0206. Min Act: -0.0002

Data Index: 749890 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1024798 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0002

Data Index: 40082 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1129260 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0002

Data Index: 808406 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0002

Data Index: 951966 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0002

Data Index: 224958 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0196. Min Act: -0.0002

Data Index: 972985 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1281563 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0002

Data Index: 393436 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0002

Data Index: 571974 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0198. Min Act: -0.0002

Data Index: 658950 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0197. Min Act: -0.0002

Data Index: 919308 (C4 (Web Text))

Max Activating Token Index: 276