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

Dataset: The Pile

Neuron 3735 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: 5.8391. Min Range: -5.8391

Max Act: 5.3101. Min Act: -0.0000

Data Index: 517086 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.8391. Min Act: -0.0000

Data Index: 121266 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3433. Min Act: -0.0000

Data Index: 1900635 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.9465. Min Act: -0.0000

Data Index: 470749 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.2400. Min Act: -0.0000

Data Index: 1350535 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.1744. Min Act: -0.0000

Data Index: 60938 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.1494. Min Act: -0.0000

Data Index: 34756 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.8904. Min Act: -0.0000

Data Index: 1785064 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4294. Min Act: -0.0000

Data Index: 627408 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.2346. Min Act: -0.0000

Data Index: 1671588 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5736. Min Act: -0.0000

Data Index: 1320146 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.6948. Min Act: -0.0000

Data Index: 1530120 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 5.8391. Min Range: -5.8391

Max Act: 3.5798. Min Act: -0.0000

Data Index: 1033664 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 5.8391. Min Range: -5.8391

Max Act: 3.4355. Min Act: -0.0000

Data Index: 213990 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 5.8391. Min Range: -5.8391

Max Act: 3.1848. Min Act: -0.0000

Data Index: 234492 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 5.8391. Min Range: -5.8391

Max Act: 3.0838. Min Act: -0.0000

Data Index: 1213470 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 5.8391. Min Range: -5.8391

Max Act: 2.5216. Min Act: -0.0000

Data Index: 913552 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 5.8391. Min Range: -5.8391

Max Act: 2.6790. Min Act: -0.0000

Data Index: 71810 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 5.8391. Min Range: -5.8391

Max Act: 2.4171. Min Act: -0.0000

Data Index: 1847835 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 5.8391. Min Range: -5.8391

Max Act: 2.5091. Min Act: -0.0000

Data Index: 1671875 (The Pile)

Max Activating Token Index: 807