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

Dataset: The Pile

Neuron 3304 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: 1.7680. Min Range: -1.7680

Max Act: 1.7396. Min Act: -0.0000

Data Index: 577140 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.7680. Min Act: -0.0000

Data Index: 393365 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1314509 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.5422. Min Act: -0.0000

Data Index: 961758 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.1564. Min Act: -0.0000

Data Index: 256334 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.2981. Min Act: -0.0000

Data Index: 872594 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1901882 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.5499. Min Act: -0.0000

Data Index: 832192 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1932101 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1574237 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1038998 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.4281. Min Act: -0.0000

Data Index: 165710 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.5874. Min Act: -0.0000

Data Index: 1735540 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.6128. Min Act: -0.0000

Data Index: 980778 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.4120. Min Act: -0.0000

Data Index: 809376 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1799946 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.6026. Min Act: -0.0000

Data Index: 437420 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.4137. Min Act: -0.0000

Data Index: 544720 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.3798. Min Act: -0.0000

Data Index: 770976 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.7680. Min Range: -1.7680

Max Act: 1.2572. Min Act: -0.0000

Data Index: 36897 (The Pile)

Max Activating Token Index: 319