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

Dataset: The Pile

Neuron 1967 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: 0.0000

Data Index: 1898457 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0977. Min Act: 0.0000

Data Index: 346722 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0974. Min Act: 0.0000

Data Index: 300932 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1459073 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0920. Min Act: 0.0000

Data Index: 1877567 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0893. Min Act: 0.0000

Data Index: 1852775 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0816. Min Act: -0.0000

Data Index: 392363 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1673174 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0828. Min Act: -0.0000

Data Index: 215269 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0812. Min Act: -0.0000

Data Index: 894454 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0812. Min Act: 0.0000

Data Index: 391325 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1817251 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0834. Min Act: -0.0000

Data Index: 68214 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0802. Min Act: -0.0000

Data Index: 989377 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1530044 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0791. Min Act: 0.0000

Data Index: 1253822 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0780. Min Act: -0.0000

Data Index: 137391 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0776. Min Act: 0.0000

Data Index: 1483355 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0772. Min Act: 0.0000

Data Index: 20410 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0771. Min Act: 0.0000

Data Index: 1508674 (The Pile)

Max Activating Token Index: 1023