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

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

Neuron 4386 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: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1302994 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1161793 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0286. Min Act: -0.0002

Data Index: 129338 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0002

Data Index: 877709 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0002

Data Index: 439244 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0002

Data Index: 820103 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0002

Data Index: 235424 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0262. Min Act: -0.0002

Data Index: 377539 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0260. Min Act: -0.0002

Data Index: 612034 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0253. Min Act: -0.0002

Data Index: 432683 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1255186 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0255. Min Act: -0.0002

Data Index: 22297 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0253. Min Act: -0.0002

Data Index: 577783 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1308430 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0251. Min Act: -0.0002

Data Index: 160251 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1080368 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0254. Min Act: -0.0002

Data Index: 880970 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0247. Min Act: -0.0002

Data Index: 767895 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0246. Min Act: -0.0002

Data Index: 257901 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1041146 (C4 (Web Text))

Max Activating Token Index: 786