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

Dataset: The Pile

Neuron 352 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2617. Min Act: -0.0000

Data Index: 66910 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1443005 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2414. Min Act: -0.0000

Data Index: 972325 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1987560 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2279. Min Act: -0.0000

Data Index: 356868 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1879776 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1530761 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2077. Min Act: -0.0000

Data Index: 571867 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1462340 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1731313 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1067474 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1494850 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1687629 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2124. Min Act: -0.0000

Data Index: 290741 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1884017 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1300097 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1785459 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1114660 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1877. Min Act: -0.0000

Data Index: 374347 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1411440 (The Pile)

Max Activating Token Index: 646