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

Dataset: The Pile

Neuron 2537 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: 0.6683. Min Range: -0.6683

Max Act: 0.6683. Min Act: -0.0000

Data Index: 272805 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6454. Min Act: -0.0000

Data Index: 674428 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6404. Min Act: -0.0000

Data Index: 717147 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5934. Min Act: -0.0000

Data Index: 500770 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5826. Min Act: -0.0000

Data Index: 775885 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5586. Min Act: -0.0000

Data Index: 21528 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5854. Min Act: -0.0000

Data Index: 720413 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1653674 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1395731 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1434424 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6007. Min Act: -0.0000

Data Index: 597055 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4440. Min Act: -0.0000

Data Index: 145820 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4580. Min Act: -0.0000

Data Index: 435845 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1443766 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1445969 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1075828 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4735. Min Act: -0.0000

Data Index: 316667 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4714. Min Act: -0.0000

Data Index: 675388 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4810. Min Act: -0.0000

Data Index: 523232 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4291. Min Act: -0.0000

Data Index: 808166 (The Pile)

Max Activating Token Index: 196