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

Dataset: The Pile

Neuron 1168 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: 1.3585. Min Range: -1.3585

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1688346 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0689. Min Act: -0.0000

Data Index: 4896 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9462. Min Act: -0.0000

Data Index: 610168 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1087491 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0058. Min Act: -0.0000

Data Index: 534876 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1339958 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9518. Min Act: -0.0000

Data Index: 164917 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9439. Min Act: -0.0000

Data Index: 355896 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1496960 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1984944 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1348080 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1080858 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1196347 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1293815 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1319648 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8764. Min Act: -0.0000

Data Index: 765689 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1862361 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1432818 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1070846 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1824470 (The Pile)

Max Activating Token Index: 24