Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.5111. Min Act: -0.0000

Data Index: 268075 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1502923 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4769. Min Act: -0.0000

Data Index: 425351 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1770993 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4224. Min Act: -0.0000

Data Index: 615608 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1229225 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3933. Min Act: -0.0000

Data Index: 407929 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1056895 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1499034 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3941. Min Act: -0.0000

Data Index: 525039 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4095. Min Act: -0.0000

Data Index: 477707 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4120. Min Act: -0.0000

Data Index: 146137 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1243653 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3975. Min Act: -0.0000

Data Index: 562496 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1981686 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1089305 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1050338 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3521. Min Act: -0.0000

Data Index: 359627 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3924. Min Act: -0.0000

Data Index: 933442 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1211201 (The Pile)

Max Activating Token Index: 293