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

Dataset: The Pile

Neuron 4829 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: 1.2713. Min Range: -1.2713

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1145962 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0678. Min Act: -0.0000

Data Index: 388092 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1446105 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0222. Min Act: -0.0000

Data Index: 612807 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0088. Min Act: -0.0000

Data Index: 252850 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0149. Min Act: -0.0000

Data Index: 600933 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1619654 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9342. Min Act: -0.0000

Data Index: 838444 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 1.2713. Min Range: -1.2713

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1873660 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9909. Min Act: -0.0000

Data Index: 995927 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1851732 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1409085 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1906160 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1177587 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1334649 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1022476 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8884. Min Act: -0.0000

Data Index: 972990 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1459631 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8854. Min Act: -0.0000

Data Index: 79020 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 1.2713. Min Range: -1.2713

Max Act: 0.8265. Min Act: -0.0000

Data Index: 433553 (The Pile)

Max Activating Token Index: 601