Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1440005 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3882. Min Act: -0.0000

Data Index: 817301 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3275. Min Act: -0.0000

Data Index: 37903 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3194. Min Act: -0.0000

Data Index: 42381 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1929434 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1370749 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1472349 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1980270 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1504508 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1090134 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2990. Min Act: -0.0000

Data Index: 26648 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1565753 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1358171 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2387. Min Act: -0.0000

Data Index: 171831 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1729421 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1388758 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1567927 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2289. Min Act: -0.0000

Data Index: 728962 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1345722 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1306883 (The Pile)

Max Activating Token Index: 609