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

Dataset: The Pile

Neuron 491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5794. Min Act: -0.0000

Data Index: 894342 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.3895. Min Act: -0.0000

Data Index: 1267910 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.2265. Min Act: -0.0000

Data Index: 1053780 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.6375. Min Act: -0.0000

Data Index: 1090200 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.3439. Min Act: -0.0000

Data Index: 228265 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.2380. Min Act: -0.0000

Data Index: 97764 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.2777. Min Act: -0.0000

Data Index: 1353997 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.0441. Min Act: -0.0000

Data Index: 418569 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.9096. Min Act: -0.0000

Data Index: 959574 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.6393. Min Act: -0.0000

Data Index: 934947 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.7567. Min Act: -0.0000

Data Index: 1775748 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.5396. Min Act: -0.0000

Data Index: 1900305 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.5886. Min Act: -0.0000

Data Index: 584161 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.5792. Min Act: -0.0000

Data Index: 1341313 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.6016. Min Act: -0.0000

Data Index: 1371726 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.4788. Min Act: -0.0000

Data Index: 1378249 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.6034. Min Act: -0.0000

Data Index: 1050613 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.7115. Min Act: -0.0000

Data Index: 899588 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.5918. Min Act: -0.0000

Data Index: 320753 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 3.6375. Min Range: -3.6375

Max Act: 2.5726. Min Act: -0.0000

Data Index: 434484 (The Pile)

Max Activating Token Index: 5