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

Dataset: The Pile

Neuron 3144 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: 0.5115. Min Range: -0.5115

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1711470 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1739395 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1803724 (The Pile)

Max Activating Token Index: 881

Text #3

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1060531 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1568571 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1715747 (The Pile)

Max Activating Token Index: 724

Text #6

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4778. Min Act: -0.0000

Data Index: 815690 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4489. Min Act: -0.0000

Data Index: 825759 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4318. Min Act: -0.0000

Data Index: 62979 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4552. Min Act: -0.0000

Data Index: 930184 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4823. Min Act: -0.0000

Data Index: 72296 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4708. Min Act: -0.0000

Data Index: 580906 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.5115. Min Act: -0.0000

Data Index: 882386 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1982596 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4316. Min Act: -0.0000

Data Index: 480901 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1755551 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1762422 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1352183 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4108. Min Act: -0.0000

Data Index: 737852 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4266. Min Act: -0.0000

Data Index: 147917 (The Pile)

Max Activating Token Index: 529