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

Dataset: The Pile

Neuron 851 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.7012. Min Act: -0.0000

Data Index: 864444 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1678908 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1095406 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1454667 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1071990 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4659. Min Act: -0.0000

Data Index: 741128 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1018053 (The Pile)

Max Activating Token Index: 780

Text #7

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1366804 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1335850 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3742. Min Act: -0.0000

Data Index: 427656 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1402543 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1639729 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1218007 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1014980 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1549489 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1597. Min Act: -0.0000

Data Index: 74389 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1755434 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1360. Min Act: -0.0000

Data Index: 984126 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1476787 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1847440 (The Pile)

Max Activating Token Index: 716