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

Dataset: The Pile

Neuron 3986 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: 0.5023. Min Range: -0.5023

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1661353 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1760151 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3991. Min Act: -0.0000

Data Index: 628895 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1195219 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1357649 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1490929 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3210. Min Act: -0.0000

Data Index: 571715 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2759. Min Act: -0.0000

Data Index: 6929 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1385061 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1000662 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1397303 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1416715 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1426856 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2537. Min Act: -0.0000

Data Index: 794824 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1457392 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2610. Min Act: -0.0000

Data Index: 206584 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1886704 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2737. Min Act: -0.0000

Data Index: 326492 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2614. Min Act: -0.0000

Data Index: 86534 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.2714. Min Act: -0.0000

Data Index: 286035 (The Pile)

Max Activating Token Index: 671