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

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

Neuron 3862 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0003

Data Index: 877546 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1404664 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1649862 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1419617 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1616626 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1589659 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1559052 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1438922 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1510341 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1383258 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1575332 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1434848 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1510717 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1439821 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1502632 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1552927 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1612412 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1399731 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1431270 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1416163 (Python Code)

Max Activating Token Index: 42