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

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

Neuron 3123 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.1008. Min Act: -0.0003

Data Index: 988734 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0951. Min Act: -0.0003

Data Index: 1281511 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0954. Min Act: -0.0003

Data Index: 302336 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1284589 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0928. Min Act: -0.0003

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0956. Min Act: -0.0003

Data Index: 1134437 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0911. Min Act: -0.0002

Data Index: 212722 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0911. Min Act: -0.0003

Data Index: 52015 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0912. Min Act: -0.0003

Data Index: 373409 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0913. Min Act: -0.0003

Data Index: 976352 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1254788 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0883. Min Act: -0.0003

Data Index: 368247 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0893. Min Act: -0.0003

Data Index: 411290 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0864. Min Act: -0.0003

Data Index: 396205 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0844. Min Act: -0.0003

Data Index: 368653 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0849. Min Act: -0.0003

Data Index: 861440 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1019965 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0860. Min Act: -0.0003

Data Index: 120522 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1240191 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0841. Min Act: -0.0003

Data Index: 481883 (C4 (Web Text))

Max Activating Token Index: 63