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

Dataset: The Pile

Neuron 4309 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: 0.5017. Min Range: -0.5017

Max Act: 0.5017. Min Act: -0.0000

Data Index: 691389 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1131400 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4441. Min Act: -0.0000

Data Index: 563125 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1251806 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1380822 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3938. Min Act: -0.0000

Data Index: 51771 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3637. Min Act: -0.0000

Data Index: 131725 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1780094 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1763711 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3964. Min Act: -0.0000

Data Index: 603244 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1818630 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1081509 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1184158 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3709. Min Act: -0.0000

Data Index: 845232 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1684235 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1981509 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1602956 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1906764 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3930. Min Act: -0.0000

Data Index: 552453 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1099901 (The Pile)

Max Activating Token Index: 776