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

Dataset: The Pile

Neuron 5051 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.7730. Min Act: -0.0000

Data Index: 1058710 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.5386. Min Act: -0.0000

Data Index: 103715 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.6310. Min Act: -0.0000

Data Index: 522839 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1324271 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1202252 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.5500. Min Act: -0.0000

Data Index: 632287 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.5892. Min Act: -0.0000

Data Index: 1947650 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1461341 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3204. Min Act: -0.0000

Data Index: 384781 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3209. Min Act: -0.0000

Data Index: 643939 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3928. Min Act: -0.0000

Data Index: 390440 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1173845 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1900337 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1172518 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3958. Min Act: -0.0000

Data Index: 756973 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3154. Min Act: -0.0000

Data Index: 175277 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3825. Min Act: -0.0000

Data Index: 922660 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1040348 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1972561 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1357805 (The Pile)

Max Activating Token Index: 205