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

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

Neuron 1011 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.6052. Min Act: -0.0002

Data Index: 970218 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.5148. Min Act: -0.0002

Data Index: 954986 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4498. Min Act: -0.0002

Data Index: 218806 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4420. Min Act: -0.0002

Data Index: 181969 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3882. Min Act: -0.0002

Data Index: 1003412 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4187. Min Act: -0.0002

Data Index: 231541 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.5326. Min Act: -0.0002

Data Index: 912940 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3685. Min Act: -0.0002

Data Index: 411175 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3796. Min Act: -0.0002

Data Index: 997770 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3351. Min Act: -0.0002

Data Index: 752661 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4297. Min Act: -0.0002

Data Index: 341041 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4623. Min Act: -0.0002

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3853. Min Act: -0.0002

Data Index: 307448 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3472. Min Act: -0.0002

Data Index: 1127136 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3688. Min Act: -0.0002

Data Index: 714361 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.2957. Min Act: -0.0002

Data Index: 1142910 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4002. Min Act: -0.0002

Data Index: 638366 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3045. Min Act: -0.0002

Data Index: 378355 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.4036. Min Act: -0.0002

Data Index: 1184579 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.6052. Min Range: -1.6052

Max Act: 1.3752. Min Act: -0.0002

Data Index: 1347098 (C4 (Web Text))

Max Activating Token Index: 933