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

Dataset: The Pile

Neuron 1713 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: 1.2653. Min Range: -1.2653

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1458206 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1817941 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0417. Min Act: -0.0000

Data Index: 269553 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9726. Min Act: -0.0000

Data Index: 397305 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1352238 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1178609 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.7630. Min Act: -0.0000

Data Index: 69416 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.7206. Min Act: -0.0000

Data Index: 225896 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6213. Min Act: -0.0000

Data Index: 973897 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1748456 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6937. Min Act: -0.0000

Data Index: 677919 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6344. Min Act: -0.0000

Data Index: 471185 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1664551 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6305. Min Act: -0.0000

Data Index: 284259 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.5935. Min Act: -0.0000

Data Index: 707251 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1061253 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6173. Min Act: 0.0000

Data Index: 783400 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6124. Min Act: -0.0000

Data Index: 922004 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6361. Min Act: -0.0000

Data Index: 227825 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.6152. Min Act: -0.0000

Data Index: 227466 (The Pile)

Max Activating Token Index: 603