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

Dataset: The Pile

Neuron 2998 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1653372 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1766573 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1101218 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.1008. Min Act: -0.0000

Data Index: 748035 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.1454. Min Act: -0.0000

Data Index: 710587 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0948. Min Act: -0.0000

Data Index: 687762 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1566144 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1977052 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0926. Min Act: -0.0000

Data Index: 868043 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0876. Min Act: -0.0000

Data Index: 632458 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1207675 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1641704 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1280813 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0759. Min Act: -0.0000

Data Index: 109428 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1736914 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1598532 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1893887 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0767. Min Act: -0.0000

Data Index: 459301 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1991166 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.2604. Min Range: -0.2604

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1533355 (The Pile)

Max Activating Token Index: 793