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

Dataset: The Pile

Neuron 3000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.0006. Min Range: -7.0006

Max Act: 7.0006. Min Act: -0.0000

Data Index: 636488 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 7.0006. Min Range: -7.0006

Max Act: 6.3363. Min Act: -0.0000

Data Index: 1979420 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.5598. Min Act: -0.0000

Data Index: 196525 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.6730. Min Act: -0.0000

Data Index: 1706807 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.3086. Min Act: -0.0000

Data Index: 202446 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.4906. Min Act: -0.0000

Data Index: 1440782 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.2708. Min Act: 0.0000

Data Index: 1486743 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.7430. Min Act: -0.0000

Data Index: 1400268 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.5456. Min Act: -0.0000

Data Index: 1990549 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.0110. Min Act: -0.0000

Data Index: 1217395 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.0137. Min Act: -0.0000

Data Index: 904320 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 7.0006. Min Range: -7.0006

Max Act: 5.0263. Min Act: -0.0000

Data Index: 371767 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.9241. Min Act: -0.0000

Data Index: 1539714 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.6113. Min Act: 0.0000

Data Index: 1479721 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.1641. Min Act: -0.0000

Data Index: 1427707 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.6857. Min Act: -0.0000

Data Index: 1876358 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.2060. Min Act: -0.0000

Data Index: 1396166 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.8372. Min Act: -0.0000

Data Index: 764709 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.5509. Min Act: -0.0000

Data Index: 664491 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 7.0006. Min Range: -7.0006

Max Act: 4.7617. Min Act: -0.0000

Data Index: 1972822 (The Pile)

Max Activating Token Index: 1006