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

Dataset: The Pile

Neuron 1790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.3737. Min Act: -0.0000

Data Index: 488063 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1033446 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2060. Min Act: -0.0000

Data Index: 214235 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1233. Min Act: -0.0000

Data Index: 263096 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1660576 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1484484 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8638. Min Act: -0.0000

Data Index: 641573 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1219339 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1408358 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9054. Min Act: -0.0000

Data Index: 953899 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8449. Min Act: -0.0000

Data Index: 644740 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9001. Min Act: -0.0000

Data Index: 391522 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1897331 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1469811 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1598575 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1135440 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8870. Min Act: -0.0000

Data Index: 279808 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8367. Min Act: -0.0000

Data Index: 2478 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.7845. Min Act: -0.0000

Data Index: 654584 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.8316. Min Act: -0.0000

Data Index: 247607 (The Pile)

Max Activating Token Index: 252