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

Dataset: The Pile

Neuron 4224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.8729. Min Act: -0.0000

Data Index: 1067187 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4800. Min Act: -0.0000

Data Index: 102149 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1258722 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1372973 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.2684. Min Act: -0.0000

Data Index: 549915 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1914. Min Act: -0.0000

Data Index: 865910 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1844. Min Act: -0.0000

Data Index: 235236 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1104. Min Act: -0.0000

Data Index: 1913239 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1094. Min Act: -0.0000

Data Index: 194527 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0762. Min Act: -0.0000

Data Index: 298090 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1221755 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0311. Min Act: -0.0000

Data Index: 500416 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0368. Min Act: -0.0000

Data Index: 676182 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1014. Min Act: -0.0000

Data Index: 1045664 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0472. Min Act: -0.0000

Data Index: 312242 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.9784. Min Act: -0.0000

Data Index: 557445 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0241. Min Act: -0.0000

Data Index: 844612 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.9941. Min Act: -0.0000

Data Index: 748827 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1228406 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1696. Min Act: -0.0000

Data Index: 178793 (The Pile)

Max Activating Token Index: 681