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

Dataset: The Pile

Neuron 4063 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: 5.7017. Min Range: -5.7017

Max Act: 5.7017. Min Act: -0.0000

Data Index: 1444302 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 5.7017. Min Range: -5.7017

Max Act: 5.3802. Min Act: -0.0000

Data Index: 277736 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 5.7017. Min Range: -5.7017

Max Act: 5.3884. Min Act: -0.0000

Data Index: 1312916 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 5.7017. Min Range: -5.7017

Max Act: 5.4465. Min Act: -0.0000

Data Index: 775550 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.9048. Min Act: -0.0000

Data Index: 512759 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 5.7017. Min Range: -5.7017

Max Act: 5.0007. Min Act: -0.0000

Data Index: 1677948 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 5.7017. Min Range: -5.7017

Max Act: 5.3355. Min Act: -0.0000

Data Index: 1762867 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.8422. Min Act: -0.0000

Data Index: 76429 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.4669. Min Act: -0.0000

Data Index: 616852 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.8261. Min Act: -0.0000

Data Index: 1470599 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.4521. Min Act: -0.0000

Data Index: 1205968 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.9704. Min Act: -0.0000

Data Index: 470675 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.7790. Min Act: -0.0000

Data Index: 1140886 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.7355. Min Act: -0.0000

Data Index: 1313417 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.6662. Min Act: -0.0000

Data Index: 1920531 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.1639. Min Act: -0.0000

Data Index: 954315 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.5015. Min Act: -0.0000

Data Index: 150189 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.6121. Min Act: -0.0000

Data Index: 1388714 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.8212. Min Act: -0.0000

Data Index: 1008517 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 5.7017. Min Range: -5.7017

Max Act: 4.6326. Min Act: -0.0000

Data Index: 684227 (The Pile)

Max Activating Token Index: 87