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

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

Neuron 3077 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: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1495759 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0259. Min Act: -0.0002

Data Index: 693090 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1248780 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1369308 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1419104 (Python Code)

Max Activating Token Index: 132

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1592092 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1455720 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0230. Min Act: -0.0002

Data Index: 570645 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1501482 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0218. Min Act: -0.0002

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1572497 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1492213 (Python Code)

Max Activating Token Index: 728

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0229. Min Act: -0.0002

Data Index: 938458 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1087906 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1485092 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1600188 (Python Code)

Max Activating Token Index: 736

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1501038 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1557848 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0212. Min Act: -0.0002

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 405