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

Dataset: The Pile

Neuron 100 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: 1.0267. Min Range: -1.0267

Max Act: 1.0022. Min Act: -0.0000

Data Index: 210060 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.0267. Min Range: -1.0267

Max Act: 1.0267. Min Act: -0.0000

Data Index: 200051 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.9609. Min Act: -0.0000

Data Index: 842923 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.9399. Min Act: -0.0000

Data Index: 345847 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8924. Min Act: -0.0000

Data Index: 601303 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1456890 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8671. Min Act: -0.0000

Data Index: 109695 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1996870 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8173. Min Act: -0.0000

Data Index: 570502 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8328. Min Act: -0.0000

Data Index: 296444 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8187. Min Act: -0.0000

Data Index: 994841 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8011. Min Act: -0.0000

Data Index: 956076 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8421. Min Act: -0.0000

Data Index: 571134 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1037887 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8201. Min Act: -0.0000

Data Index: 957462 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8606. Min Act: -0.0000

Data Index: 566503 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1722106 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8073. Min Act: -0.0000

Data Index: 876645 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8306. Min Act: -0.0000

Data Index: 823688 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 1.0267. Min Range: -1.0267

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1431751 (The Pile)

Max Activating Token Index: 376