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

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

Neuron 488 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0000

Data Index: 697361 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1392958 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1400498 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1533142 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0243. Min Act: -0.0000

Data Index: 1641553 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0240. Min Act: -0.0000

Data Index: 1522341 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1394808 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0160. Min Act: -0.0000

Data Index: 1654179 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1503633 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0204. Min Act: -0.0000

Data Index: 580788 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0240. Min Act: -0.0000

Data Index: 157092 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1594388 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1601204 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1570108 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1582910 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0200. Min Act: -0.0000

Data Index: 1579279 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1579083 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0214. Min Act: -0.0000

Data Index: 1566983 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1590101 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0184. Min Act: -0.0000

Data Index: 50983 (C4 (Web Text))

Max Activating Token Index: 187