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

Dataset: The Pile

Neuron 1051 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1988473 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7681. Min Act: -0.0000

Data Index: 476636 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6632. Min Act: -0.0000

Data Index: 1700507 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1136957 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7556. Min Act: -0.0000

Data Index: 490903 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6177. Min Act: -0.0000

Data Index: 1334605 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1617174 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6915. Min Act: -0.0000

Data Index: 157007 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.5611. Min Act: -0.0000

Data Index: 180416 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6532. Min Act: -0.0000

Data Index: 663204 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1037047 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6030. Min Act: -0.0000

Data Index: 98577 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1406190 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1234438 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.4758. Min Act: -0.0000

Data Index: 501803 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1307653 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1657877 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3592. Min Act: -0.0000

Data Index: 527246 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1654882 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3202. Min Act: -0.0000

Data Index: 841658 (The Pile)

Max Activating Token Index: 171