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

Dataset: The Pile

Neuron 3306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7851. Min Act: -0.0000

Data Index: 779844 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1397276 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1282739 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5237. Min Act: -0.0000

Data Index: 7455 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5265. Min Act: -0.0000

Data Index: 953274 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1756489 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1289018 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1502766 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5012. Min Act: -0.0000

Data Index: 675719 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1042442 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1047068 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1452850 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1477395 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4004. Min Act: -0.0000

Data Index: 677682 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1128480 (The Pile)

Max Activating Token Index: 888

Text #15

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.3859. Min Act: -0.0000

Data Index: 383809 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.3739. Min Act: -0.0000

Data Index: 320325 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1216452 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1882587 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.3806. Min Act: -0.0000

Data Index: 367414 (The Pile)

Max Activating Token Index: 961