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

Dataset: The Pile

Neuron 3614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1506448 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1652288 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1609757 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9924. Min Act: -0.0000

Data Index: 546889 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0502. Min Act: -0.0000

Data Index: 626458 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9746. Min Act: -0.0000

Data Index: 113208 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0100. Min Act: -0.0000

Data Index: 856030 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1569412 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1438991 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9285. Min Act: -0.0000

Data Index: 558561 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1192637 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0489. Min Act: -0.0000

Data Index: 937519 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1004056 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9259. Min Act: -0.0000

Data Index: 553840 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1520580 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8268. Min Act: -0.0000

Data Index: 352112 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9200. Min Act: -0.0000

Data Index: 395457 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9086. Min Act: -0.0000

Data Index: 620860 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9376. Min Act: -0.0000

Data Index: 20069 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1256507 (The Pile)

Max Activating Token Index: 639