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

Dataset: The Pile

Neuron 3405 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: 1.7804. Min Range: -1.7804

Max Act: 1.7804. Min Act: -0.0000

Data Index: 1156343 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5888. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4322. Min Act: -0.0000

Data Index: 107 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6962. Min Act: -0.0000

Data Index: 326441 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5653. Min Act: -0.0000

Data Index: 285144 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5776. Min Act: -0.0000

Data Index: 845513 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3965. Min Act: -0.0000

Data Index: 282631 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3397. Min Act: 0.0000

Data Index: 1038087 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1561686 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1683848 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1457413 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.1834. Min Act: -0.0000

Data Index: 760428 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1449423 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1573462 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.0408. Min Act: 0.0000

Data Index: 1616074 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.0699. Min Act: -0.0000

Data Index: 727691 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.1254. Min Act: -0.0000

Data Index: 524397 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1476358 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 1.7804. Min Range: -1.7804

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1103859 (The Pile)

Max Activating Token Index: 498