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

Dataset: The Pile

Neuron 4400 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: 0.9422. Min Range: -0.9422

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1003930 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1335496 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7436. Min Act: -0.0000

Data Index: 980346 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1462094 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1075026 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1872897 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1386261 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1515256 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5905. Min Act: -0.0000

Data Index: 172409 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6033. Min Act: -0.0000

Data Index: 839150 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1219781 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1799849 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5971. Min Act: -0.0000

Data Index: 150598 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1749935 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5864. Min Act: -0.0000

Data Index: 648557 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5791. Min Act: -0.0000

Data Index: 352435 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5747. Min Act: -0.0000

Data Index: 897048 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5723. Min Act: -0.0000

Data Index: 451231 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1131989 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1114601 (The Pile)

Max Activating Token Index: 61