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

Dataset: The Pile

Neuron 257 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: 0.1411. Min Range: -0.1411

Max Act: 0.1411. Min Act: -0.0000

Data Index: 675023 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0797. Min Act: -0.0000

Data Index: 352551 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0827. Min Act: -0.0000

Data Index: 45816 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0721. Min Act: -0.0000

Data Index: 280839 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0793. Min Act: -0.0000

Data Index: 896488 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1795030 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0770. Min Act: -0.0000

Data Index: 308007 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0730. Min Act: -0.0000

Data Index: 614979 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0790. Min Act: -0.0000

Data Index: 210698 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0707. Min Act: -0.0000

Data Index: 762538 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0766. Min Act: -0.0000

Data Index: 352025 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1506164 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1795937 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1385740 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1892980 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1518347 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0593. Min Act: -0.0000

Data Index: 198330 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0713. Min Act: -0.0000

Data Index: 100595 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1575046 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0624. Min Act: -0.0000

Data Index: 634608 (The Pile)

Max Activating Token Index: 798