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

Dataset: The Pile

Neuron 1535 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4212. Min Act: -0.0000

Data Index: 732709 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3947. Min Act: -0.0000

Data Index: 779371 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1496884 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1007716 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1959918 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1229912 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4509. Min Act: -0.0000

Data Index: 911140 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1927802 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1441317 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3483. Min Act: -0.0000

Data Index: 426726 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1760909 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1130566 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1706000 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3213. Min Act: -0.0000

Data Index: 622849 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3275. Min Act: -0.0000

Data Index: 767627 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1279548 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3265. Min Act: 0.0000

Data Index: 964007 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1264819 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1176549 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3400. Min Act: -0.0000

Data Index: 249946 (The Pile)

Max Activating Token Index: 867