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

Dataset: The Pile

Neuron 821 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: 0.9594. Min Range: -0.9594

Max Act: 0.9594. Min Act: -0.0000

Data Index: 505777 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8488. Min Act: -0.0000

Data Index: 708748 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1584019 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7927. Min Act: -0.0000

Data Index: 397740 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7908. Min Act: -0.0000

Data Index: 72247 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1879889 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1130294 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1206560 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1625317 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6733. Min Act: -0.0000

Data Index: 597113 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1325333 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1223374 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6971. Min Act: -0.0000

Data Index: 135775 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1870887 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6714. Min Act: -0.0000

Data Index: 530123 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6598. Min Act: -0.0000

Data Index: 130854 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6368. Min Act: -0.0000

Data Index: 8780 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1432539 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6584. Min Act: -0.0000

Data Index: 798784 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6141. Min Act: -0.0000

Data Index: 235927 (The Pile)

Max Activating Token Index: 868