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

Dataset: The Pile

Neuron 350 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: 0.9815. Min Range: -0.9815

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1073301 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8914. Min Act: -0.0000

Data Index: 593349 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1981016 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1733963 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7803. Min Act: -0.0000

Data Index: 473159 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1046213 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1318910 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1011940 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5559. Min Act: 0.0000

Data Index: 1619022 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5887. Min Act: 0.0000

Data Index: 182213 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1141309 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5636. Min Act: 0.0000

Data Index: 662363 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1176458 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5580. Min Act: -0.0000

Data Index: 938596 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1747874 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1923208 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1064895 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5278. Min Act: -0.0000

Data Index: 721976 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5283. Min Act: -0.0000

Data Index: 491032 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.5459. Min Act: -0.0000

Data Index: 104369 (The Pile)

Max Activating Token Index: 514