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

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

Neuron 3104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1426820 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1417026 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1440169 (Python Code)

Max Activating Token Index: 558

Text #3

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1418067 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1560774 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1654267 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0918. Min Act: -0.0000

Data Index: 414201 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0876. Min Act: -0.0000

Data Index: 949974 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0838. Min Act: -0.0000

Data Index: 934629 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0869. Min Act: -0.0000

Data Index: 948070 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1556908 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1499857 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0917. Min Act: -0.0000

Data Index: 141224 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1463847 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1458187 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1038619 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1598779 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1507373 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1051852 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1580092 (Python Code)

Max Activating Token Index: 320