Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1431977 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1008564 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5170. Min Act: -0.0000

Data Index: 851218 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4700. Min Act: -0.0000

Data Index: 426306 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4021. Min Act: -0.0000

Data Index: 726912 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3991. Min Act: -0.0000

Data Index: 874336 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1120322 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1420945 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1900994 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1127626 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3647. Min Act: -0.0000

Data Index: 630818 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3394. Min Act: -0.0000

Data Index: 888160 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3459. Min Act: -0.0000

Data Index: 310973 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1761343 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1768118 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3344. Min Act: -0.0000

Data Index: 575464 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3522. Min Act: -0.0000

Data Index: 949589 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3525. Min Act: -0.0000

Data Index: 701960 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3102. Min Act: -0.0000

Data Index: 61557 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3395. Min Act: -0.0000

Data Index: 627158 (The Pile)

Max Activating Token Index: 464