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

Dataset: The Pile

Neuron 3778 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: 0.5240. Min Range: -0.5240

Max Act: 0.5153. Min Act: -0.0000

Data Index: 33417 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1841123 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4889. Min Act: -0.0000

Data Index: 740097 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1501804 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4532. Min Act: -0.0000

Data Index: 826674 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4438. Min Act: -0.0000

Data Index: 13177 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4132. Min Act: -0.0000

Data Index: 114227 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1078010 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4250. Min Act: -0.0000

Data Index: 788462 (The Pile)

Max Activating Token Index: 391

Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4193. Min Act: -0.0000

Data Index: 765087 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4201. Min Act: -0.0000

Data Index: 162333 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4260. Min Act: -0.0000

Data Index: 772842 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1747306 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1858725 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4075. Min Act: -0.0000

Data Index: 690558 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3940. Min Act: -0.0000

Data Index: 193061 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1726268 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1580097 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1689510 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1476145 (The Pile)

Max Activating Token Index: 137