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

Dataset: The Pile

Neuron 3883 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3566. Min Act: -0.0000

Data Index: 949471 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1235227 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3212. Min Act: -0.0000

Data Index: 990437 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3265. Min Act: -0.0000

Data Index: 612859 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3076. Min Act: -0.0000

Data Index: 518530 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1484024 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1596 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1645167 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3028. Min Act: -0.0000

Data Index: 446732 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2797. Min Act: -0.0000

Data Index: 873837 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2880. Min Act: -0.0000

Data Index: 425609 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1175343 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1672031 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1853635 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1229220 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1646744 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2670. Min Act: -0.0000

Data Index: 389476 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1412616 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2629. Min Act: -0.0000

Data Index: 266715 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1004031 (The Pile)

Max Activating Token Index: 200