Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3876 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 4.0987. Min Range: -4.0987

Max Act: 4.0987. Min Act: -0.0000

Data Index: 169953 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.7657. Min Act: -0.0000

Data Index: 955042 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.6912. Min Act: -0.0000

Data Index: 1289664 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.3788. Min Act: -0.0000

Data Index: 47650 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.4667. Min Act: -0.0000

Data Index: 1518378 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.7971. Min Act: -0.0000

Data Index: 1449333 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.5497. Min Act: -0.0000

Data Index: 572925 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.4045. Min Act: -0.0000

Data Index: 1498202 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.4063. Min Act: -0.0000

Data Index: 1345789 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.7315. Min Act: -0.0000

Data Index: 1371435 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.5567. Min Act: -0.0000

Data Index: 1018724 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.6856. Min Act: -0.0000

Data Index: 1851486 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.5203. Min Act: -0.0000

Data Index: 987679 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.4006. Min Act: -0.0000

Data Index: 920434 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.3825. Min Act: -0.0000

Data Index: 1661524 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.4007. Min Act: -0.0000

Data Index: 491222 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.5131. Min Act: -0.0000

Data Index: 1897013 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.6338. Min Act: -0.0000

Data Index: 427214 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 4.0987. Min Range: -4.0987

Max Act: 2.9487. Min Act: -0.0000

Data Index: 515258 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 4.0987. Min Range: -4.0987

Max Act: 3.2799. Min Act: -0.0000

Data Index: 269100 (The Pile)

Max Activating Token Index: 343