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

Dataset: The Pile

Neuron 809 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: 0.2631. Min Range: -0.2631

Max Act: 0.2631. Min Act: -0.0000

Data Index: 380234 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2482. Min Act: -0.0000

Data Index: 879461 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2344. Min Act: -0.0000

Data Index: 294015 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1976. Min Act: -0.0000

Data Index: 530689 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1822056 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1724. Min Act: -0.0000

Data Index: 605507 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1966. Min Act: -0.0000

Data Index: 13387 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1829. Min Act: -0.0000

Data Index: 336792 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1663559 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1926073 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1760. Min Act: -0.0000

Data Index: 650768 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1510024 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1811206 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1246543 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1706. Min Act: -0.0000

Data Index: 236833 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1913. Min Act: -0.0000

Data Index: 861318 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1782940 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1483227 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1560. Min Act: -0.0000

Data Index: 444957 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1522. Min Act: -0.0000

Data Index: 952967 (The Pile)

Max Activating Token Index: 992