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

Dataset: The Pile

Neuron 2772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1172062 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1031. Min Act: -0.0000

Data Index: 92845 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1022. Min Act: -0.0000

Data Index: 548589 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1247652 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1153931 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0937. Min Act: -0.0000

Data Index: 691731 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1881009 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0941. Min Act: -0.0000

Data Index: 161162 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1287398 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0885. Min Act: -0.0000

Data Index: 277366 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1242593 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1811900 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0868. Min Act: -0.0000

Data Index: 283434 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1825891 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0847. Min Act: -0.0000

Data Index: 515709 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0839. Min Act: -0.0000

Data Index: 181014 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0817. Min Act: -0.0000

Data Index: 874351 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1911000 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1009154 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0845. Min Act: -0.0000

Data Index: 214779 (The Pile)

Max Activating Token Index: 584