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

Dataset: The Pile

Neuron 3368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1880820 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0808. Min Act: -0.0000

Data Index: 427599 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1184368 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1318401 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1608545 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0706. Min Act: -0.0000

Data Index: 658642 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1877625 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0678. Min Act: -0.0000

Data Index: 613007 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1735095 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1151714 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0737. Min Act: -0.0000

Data Index: 832146 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1587428 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1438613 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0678. Min Act: -0.0000

Data Index: 961822 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1396372 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1605020 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1284743 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0661. Min Act: -0.0000

Data Index: 891710 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1169967 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0609. Min Act: -0.0000

Data Index: 976581 (The Pile)

Max Activating Token Index: 583