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

Dataset: The Pile

Neuron 4426 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: 1.2067. Min Range: -1.2067

Max Act: 1.2067. Min Act: -0.0000

Data Index: 362933 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.0641. Min Act: 0.0000

Data Index: 322035 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1256608 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9929. Min Act: -0.0000

Data Index: 103047 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1032152 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1258242 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1663883 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1049421 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1659615 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1809208 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7598. Min Act: -0.0000

Data Index: 816548 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8493. Min Act: -0.0000

Data Index: 309558 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1770708 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8698. Min Act: -0.0000

Data Index: 76010 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7899. Min Act: -0.0000

Data Index: 972071 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7496. Min Act: -0.0000

Data Index: 517872 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7702. Min Act: -0.0000

Data Index: 30942 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1635186 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1891019 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1245909 (The Pile)

Max Activating Token Index: 521