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

Dataset: The Pile

Neuron 4121 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: 1.3498. Min Range: -1.3498

Max Act: 1.3498. Min Act: -0.0000

Data Index: 684052 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1864714 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2444. Min Act: -0.0000

Data Index: 999246 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1700. Min Act: -0.0000

Data Index: 413603 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2192. Min Act: -0.0000

Data Index: 527892 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1998085 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0240. Min Act: -0.0000

Data Index: 235506 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1257. Min Act: -0.0000

Data Index: 766888 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1481514 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1552614 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1253019 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0856. Min Act: -0.0000

Data Index: 140218 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.3498. Min Range: -1.3498

Max Act: 0.9545. Min Act: -0.0000

Data Index: 2657 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.3498. Min Range: -1.3498

Max Act: 0.8692. Min Act: -0.0000

Data Index: 248014 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0740. Min Act: -0.0000

Data Index: 182077 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 1.3498. Min Range: -1.3498

Max Act: 0.9673. Min Act: -0.0000

Data Index: 86724 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0218. Min Act: -0.0000

Data Index: 185148 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 1.3498. Min Range: -1.3498

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1990557 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.3498. Min Range: -1.3498

Max Act: 0.9660. Min Act: -0.0000

Data Index: 819613 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0031. Min Act: -0.0000

Data Index: 470353 (The Pile)

Max Activating Token Index: 996