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

Dataset: The Pile

Neuron 4232 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0003

Data Index: 1373895 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1387318 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1378552 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1426529 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1886775 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1486072 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1953933 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0355. Min Act: -0.0002

Data Index: 476569 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0317. Min Act: -0.0002

Data Index: 550261 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0312. Min Act: -0.0003

Data Index: 353798 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0311. Min Act: -0.0002

Data Index: 498718 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1204759 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1376274 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0308. Min Act: -0.0002

Data Index: 32075 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0279. Min Act: -0.0003

Data Index: 299027 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0286. Min Act: -0.0003

Data Index: 177352 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1416032 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1054782 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1739937 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0266. Min Act: -0.0002

Data Index: 542901 (The Pile)

Max Activating Token Index: 7