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

Dataset: The Pile

Neuron 4699 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: 0.8474. Min Range: -0.8474

Max Act: 0.8474. Min Act: -0.0000

Data Index: 338136 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8227. Min Act: -0.0000

Data Index: 195595 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7258. Min Act: -0.0000

Data Index: 476290 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6914. Min Act: -0.0000

Data Index: 440249 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7047. Min Act: -0.0000

Data Index: 892294 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1980763 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5940. Min Act: -0.0000

Data Index: 303944 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5926. Min Act: -0.0000

Data Index: 366762 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1452881 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5451. Min Act: -0.0000

Data Index: 561413 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1564903 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1585713 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5313. Min Act: -0.0000

Data Index: 754636 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5295. Min Act: -0.0000

Data Index: 38458 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6370. Min Act: -0.0000

Data Index: 5996 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5590. Min Act: -0.0000

Data Index: 933347 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5412. Min Act: -0.0000

Data Index: 792304 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1280703 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1184860 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1764285 (The Pile)

Max Activating Token Index: 116