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

Dataset: The Pile

Neuron 1904 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.9983. Min Act: -0.0000

Data Index: 782533 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7453. Min Act: -0.0000

Data Index: 385031 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1691128 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5886. Min Act: -0.0000

Data Index: 53168 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1164918 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1851112 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5998. Min Act: -0.0000

Data Index: 1210315 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1285885 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1365529 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1388622 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1729161 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3679. Min Act: -0.0000

Data Index: 717807 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3765. Min Act: -0.0000

Data Index: 433919 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1314800 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1428509 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3717. Min Act: -0.0000

Data Index: 959313 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.2707. Min Act: -0.0000

Data Index: 612347 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1090857 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.2505. Min Act: -0.0000

Data Index: 505482 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1657906 (The Pile)

Max Activating Token Index: 178