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

Dataset: The Pile

Neuron 3188 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: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0000

Data Index: 193748 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0937. Min Act: -0.0000

Data Index: 475289 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0833. Min Act: -0.0000

Data Index: 874224 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1113194 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0795. Min Act: -0.0000

Data Index: 253329 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0767. Min Act: -0.0000

Data Index: 160121 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0749. Min Act: -0.0000

Data Index: 23321 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1937794 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1809055 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0749. Min Act: -0.0000

Data Index: 687523 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0607. Min Act: -0.0000

Data Index: 524018 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0639. Min Act: -0.0000

Data Index: 367525 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0659. Min Act: -0.0000

Data Index: 776854 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0692. Min Act: -0.0000

Data Index: 456803 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1129661 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1786350 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1134113 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1410468 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0614. Min Act: -0.0000

Data Index: 71259 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0594. Min Act: -0.0000

Data Index: 557097 (The Pile)

Max Activating Token Index: 190