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

Dataset: The Pile

Neuron 3303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1249146 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1304282 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1614782 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1704783 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1332298 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1423770 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1529060 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1773700 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0758. Min Act: -0.0000

Data Index: 404115 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1831834 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1826856 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1371906 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1285630 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1706468 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0702. Min Act: -0.0000

Data Index: 62638 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0669. Min Act: -0.0000

Data Index: 515813 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1476245 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1979321 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0597. Min Act: -0.0000

Data Index: 577872 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1603887 (The Pile)

Max Activating Token Index: 258