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

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

Neuron 3346 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: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1609059 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0259. Min Act: -0.0002

Data Index: 688708 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1364701 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1548542 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1387615 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1580645 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1566184 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1604524 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1581577 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0235. Min Act: -0.0002

Data Index: 362361 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1523919 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1529900 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0232. Min Act: -0.0002

Data Index: 423182 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1391650 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1207964 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1432477 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1497878 (Python Code)

Max Activating Token Index: 215

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1194772 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1599113 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1516615 (Python Code)

Max Activating Token Index: 39