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

Dataset: The Pile

Neuron 2764 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: 2.6517. Min Range: -2.6517

Max Act: 2.6517. Min Act: -0.0000

Data Index: 1456602 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.6139. Min Act: -0.0000

Data Index: 1828392 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5697. Min Act: -0.0000

Data Index: 1445941 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5379. Min Act: -0.0000

Data Index: 1224148 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4426. Min Act: -0.0000

Data Index: 995426 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5050. Min Act: -0.0000

Data Index: 1871307 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3290. Min Act: -0.0000

Data Index: 926942 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2830. Min Act: -0.0000

Data Index: 1911491 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3768. Min Act: -0.0000

Data Index: 494873 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1020487 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.0876. Min Act: -0.0000

Data Index: 148781 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.1874. Min Act: -0.0000

Data Index: 790535 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 2.6517. Min Range: -2.6517

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1511285 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1657048 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.0794. Min Act: -0.0000

Data Index: 1111761 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2025. Min Act: -0.0000

Data Index: 256394 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.0954. Min Act: -0.0000

Data Index: 1110203 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 2.6517. Min Range: -2.6517

Max Act: 1.9234. Min Act: -0.0000

Data Index: 744078 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2008. Min Act: -0.0000

Data Index: 1037425 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.1679. Min Act: -0.0000

Data Index: 1961367 (The Pile)

Max Activating Token Index: 143