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

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

Neuron 1827 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0977. Min Range: -4.0977

Max Act: 4.0967. Min Act: -0.0000

Data Index: 188532 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.0977. Min Range: -4.0977

Max Act: 4.0977. Min Act: -0.0000

Data Index: 1322307 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.7569. Min Act: -0.0000

Data Index: 1256146 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.9017. Min Act: -0.0000

Data Index: 204371 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5683. Min Act: -0.0000

Data Index: 118765 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.6903. Min Act: -0.0000

Data Index: 235893 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5089. Min Act: -0.0000

Data Index: 210607 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.4822. Min Act: -0.0000

Data Index: 713139 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.6188. Min Act: -0.0000

Data Index: 727917 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5429. Min Act: -0.0000

Data Index: 1098807 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5192. Min Act: -0.0000

Data Index: 973178 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5097. Min Act: -0.0000

Data Index: 1060397 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5045. Min Act: -0.0000

Data Index: 806218 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.4870. Min Act: -0.0000

Data Index: 615872 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.4496. Min Act: -0.0000

Data Index: 1059683 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.4281. Min Act: -0.0000

Data Index: 295465 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.2311. Min Act: -0.0000

Data Index: 611199 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.3693. Min Act: -0.0000

Data Index: 380147 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.5077. Min Act: -0.0000

Data Index: 1063154 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 4.0977. Min Range: -4.0977

Max Act: 3.3372. Min Act: -0.0000

Data Index: 1169073 (C4 (Web Text))

Max Activating Token Index: 45