Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.2255. Min Act: -0.0000

Data Index: 354164 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1262316 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1227972 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1196. Min Act: -0.0000

Data Index: 329531 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0095. Min Act: -0.0000

Data Index: 241375 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1427491 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9457. Min Act: -0.0000

Data Index: 406070 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9349. Min Act: -0.0000

Data Index: 64504 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1165302 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1566272 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9343. Min Act: -0.0000

Data Index: 602762 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9430. Min Act: -0.0000

Data Index: 832400 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1612844 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9085. Min Act: -0.0000

Data Index: 14995 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1413887 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1183618 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1135768 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1441427 (Python Code)

Max Activating Token Index: 95

Text #18

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1446938 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8454. Min Act: -0.0000

Data Index: 392863 (C4 (Web Text))

Max Activating Token Index: 3