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

Dataset: The Pile

Neuron 2504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1790481 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1458160 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1246723 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1676431 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1911811 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1609821 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1461876 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1345403 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0002

Data Index: 21762 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1198024 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0717. Min Act: -0.0002

Data Index: 67710 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0814. Min Act: -0.0002

Data Index: 225014 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0894. Min Act: -0.0002

Data Index: 325766 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1440229 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1516897 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1522029 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1647588 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1522655 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1765440 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1830330 (The Pile)

Max Activating Token Index: 778