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

Dataset: The Pile

Neuron 486 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: 0.5684. Min Range: -0.5684

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1817853 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1990993 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1251250 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1322952 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1038376 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1632478 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1681659 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2806. Min Act: -0.0000

Data Index: 218776 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1641224 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1725688 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1510985 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2826. Min Act: -0.0000

Data Index: 543085 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1143851 (The Pile)

Max Activating Token Index: 892

Text #13

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1950810 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2655. Min Act: -0.0000

Data Index: 402181 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1758624 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1093663 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2616. Min Act: -0.0000

Data Index: 889328 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1209516 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2560. Min Act: -0.0000

Data Index: 107524 (The Pile)

Max Activating Token Index: 813