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

Dataset: The Pile

Neuron 1759 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1339883 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 442587 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1946377 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1997447 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 964775 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1243602 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1061096 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1417872 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 814785 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 898717 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 336242 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1566380 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1259573 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 101219 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1067906 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 456047 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 995298 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1319351 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 498690 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1941025 (The Pile)

Max Activating Token Index: 774