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

Dataset: The Pile

Neuron 3000 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: 3.6177. Min Range: -3.6177

Max Act: 3.6177. Min Act: -0.0000

Data Index: 357167 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.5245. Min Act: -0.0000

Data Index: 1142558 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.3871. Min Act: -0.0000

Data Index: 1934322 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.3184. Min Act: -0.0000

Data Index: 893059 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.6866. Min Act: -0.0000

Data Index: 283849 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1730. Min Act: -0.0000

Data Index: 1026409 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1046. Min Act: -0.0000

Data Index: 1006784 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.0838. Min Act: -0.0000

Data Index: 1583362 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.3719. Min Act: -0.0000

Data Index: 1010322 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.8022. Min Act: -0.0000

Data Index: 88384 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1886. Min Act: -0.0000

Data Index: 856945 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.0484. Min Act: -0.0000

Data Index: 1036349 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.4995. Min Act: -0.0000

Data Index: 629867 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1159. Min Act: -0.0000

Data Index: 773749 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.7814. Min Act: -0.0000

Data Index: 416095 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.0631. Min Act: -0.0000

Data Index: 301076 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.9251. Min Act: -0.0000

Data Index: 1716825 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.8958. Min Act: -0.0000

Data Index: 278673 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1618. Min Act: -0.0000

Data Index: 1296119 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.8739. Min Act: -0.0000

Data Index: 291288 (The Pile)

Max Activating Token Index: 351