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

Dataset: The Pile

Neuron 677 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1973318 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1563157 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6545. Min Act: -0.0000

Data Index: 259093 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6749. Min Act: -0.0000

Data Index: 970769 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6850. Min Act: -0.0000

Data Index: 794915 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6592. Min Act: -0.0000

Data Index: 60077 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1336890 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1468810 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1722570 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6269. Min Act: -0.0000

Data Index: 540568 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1748484 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1813668 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1454843 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6266. Min Act: -0.0000

Data Index: 360630 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6246. Min Act: -0.0000

Data Index: 890513 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1029891 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.5889. Min Act: -0.0000

Data Index: 69611 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1029044 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.6148. Min Act: -0.0000

Data Index: 133896 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.8571. Min Range: -0.8571

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1016180 (The Pile)

Max Activating Token Index: 693