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

Dataset: The Pile

Neuron 1275 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: 1.3867. Min Range: -1.3867

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1695133 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.3867. Min Act: -0.0000

Data Index: 365669 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2565. Min Act: -0.0000

Data Index: 43589 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1185. Min Act: -0.0000

Data Index: 445805 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1861989 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1840. Min Act: -0.0000

Data Index: 720161 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1269493 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0827. Min Act: -0.0000

Data Index: 486170 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1597035 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1707077 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9743. Min Act: -0.0000

Data Index: 568848 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0579. Min Act: -0.0000

Data Index: 382962 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1502900 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1864565 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0415. Min Act: -0.0000

Data Index: 172270 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1172326 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1774024 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2425. Min Act: -0.0000

Data Index: 808191 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9884. Min Act: -0.0000

Data Index: 283077 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1567992 (The Pile)

Max Activating Token Index: 460