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

Dataset: The Pile

Neuron 5017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1030622 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1911808 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1287259 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3937. Min Act: 0.0000

Data Index: 1996907 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1873868 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1145422 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3918. Min Act: 0.0000

Data Index: 670316 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3987. Min Act: -0.0000

Data Index: 901576 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4079. Min Act: -0.0000

Data Index: 786043 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3817. Min Act: 0.0000

Data Index: 333544 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1944185 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3792. Min Act: -0.0000

Data Index: 659875 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1999849 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1012041 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3831. Min Act: 0.0000

Data Index: 1940599 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3941. Min Act: -0.0000

Data Index: 941683 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3737. Min Act: 0.0000

Data Index: 1372620 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3597. Min Act: -0.0000

Data Index: 785462 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1603671 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3732. Min Act: 0.0000

Data Index: 1597616 (The Pile)

Max Activating Token Index: 327