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

Dataset: The Pile

Neuron 3758 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: 3.3801. Min Range: -3.3801

Max Act: 3.3801. Min Act: -0.0000

Data Index: 1056051 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.7781. Min Act: -0.0000

Data Index: 41810 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.6512. Min Act: -0.0000

Data Index: 1620939 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.4934. Min Act: -0.0000

Data Index: 92366 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3280. Min Act: -0.0000

Data Index: 1025948 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3125. Min Act: -0.0000

Data Index: 1991632 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.6999. Min Act: -0.0000

Data Index: 829633 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.2871. Min Act: -0.0000

Data Index: 327853 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.5252. Min Act: -0.0000

Data Index: 656430 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.1758. Min Act: -0.0000

Data Index: 582475 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3665. Min Act: -0.0000

Data Index: 900907 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3726. Min Act: -0.0000

Data Index: 763192 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3628. Min Act: -0.0000

Data Index: 614405 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.4862. Min Act: -0.0000

Data Index: 722580 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.1055. Min Act: -0.0000

Data Index: 1580168 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.3284. Min Act: -0.0000

Data Index: 78842 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.0092. Min Act: -0.0000

Data Index: 1626625 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.2207. Min Act: -0.0000

Data Index: 971030 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.0755. Min Act: -0.0000

Data Index: 704067 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 3.3801. Min Range: -3.3801

Max Act: 2.1837. Min Act: -0.0000

Data Index: 1056617 (The Pile)

Max Activating Token Index: 262