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

Dataset: The Pile

Neuron 3323 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: 1.4813. Min Range: -1.4813

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1852479 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.4813. Min Act: -0.0000

Data Index: 715022 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1542346 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1897458 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1847752 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0801. Min Act: -0.0000

Data Index: 586733 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1703842 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0892. Min Act: -0.0000

Data Index: 146183 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1866. Min Act: -0.0000

Data Index: 540336 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1310. Min Act: -0.0000

Data Index: 726463 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1870232 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0096. Min Act: -0.0000

Data Index: 816797 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.9522. Min Act: 0.0000

Data Index: 665940 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0677. Min Act: 0.0000

Data Index: 1031143 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1272. Min Act: -0.0000

Data Index: 438372 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0342. Min Act: -0.0000

Data Index: 883366 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1903374 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.9649. Min Act: -0.0000

Data Index: 300976 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.9894. Min Act: -0.0000

Data Index: 639912 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.8756. Min Act: -0.0000

Data Index: 731050 (The Pile)

Max Activating Token Index: 489