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

Dataset: The Pile

Neuron 4015 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0917. Min Act: -0.0000

Data Index: 261610 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0815. Min Act: -0.0000

Data Index: 651472 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0863. Min Act: -0.0000

Data Index: 430735 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0828. Min Act: -0.0000

Data Index: 166693 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0793. Min Act: -0.0000

Data Index: 123073 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0849. Min Act: -0.0000

Data Index: 984037 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0811. Min Act: -0.0000

Data Index: 442833 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0757. Min Act: -0.0000

Data Index: 664785 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0783. Min Act: -0.0000

Data Index: 763689 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0808. Min Act: -0.0000

Data Index: 566090 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0775. Min Act: -0.0000

Data Index: 96660 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1155499 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1990083 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0754. Min Act: -0.0000

Data Index: 221950 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1830817 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0746. Min Act: -0.0000

Data Index: 488745 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1963078 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1152765 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1127518 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1345206 (The Pile)

Max Activating Token Index: 1023