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

Dataset: The Pile

Neuron 940 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: 0.5087. Min Range: -0.5087

Max Act: 0.4717. Min Act: -0.0000

Data Index: 776566 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4452. Min Act: -0.0000

Data Index: 648481 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4627. Min Act: -0.0000

Data Index: 396473 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4841. Min Act: -0.0000

Data Index: 130149 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1784071 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4378. Min Act: -0.0000

Data Index: 457516 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1083869 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1160404 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4016. Min Act: -0.0000

Data Index: 519757 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1099515 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3546. Min Act: -0.0000

Data Index: 950020 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3318. Min Act: -0.0000

Data Index: 195912 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3230. Min Act: -0.0000

Data Index: 577071 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1451709 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1526701 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1036699 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3648. Min Act: -0.0000

Data Index: 332134 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1258304 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3376. Min Act: -0.0000

Data Index: 785573 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3243. Min Act: -0.0000

Data Index: 58240 (The Pile)

Max Activating Token Index: 386