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

Dataset: The Pile

Neuron 1052 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: 0.8916. Min Range: -0.8916

Max Act: 0.8916. Min Act: -0.0000

Data Index: 722795 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1116898 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1931411 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1903489 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1126390 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1433536 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1772460 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1563330 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6342. Min Act: -0.0000

Data Index: 79025 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1988600 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1534490 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1268969 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1072899 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4944. Min Act: -0.0000

Data Index: 333300 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4601. Min Act: -0.0000

Data Index: 307564 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4944. Min Act: -0.0000

Data Index: 665994 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1684421 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5120. Min Act: -0.0000

Data Index: 627727 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1618767 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1855894 (The Pile)

Max Activating Token Index: 591