Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.7016. Min Act: -0.0000

Data Index: 207812 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1559537 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6858. Min Act: -0.0000

Data Index: 608036 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1858465 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1942424 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1381277 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6247. Min Act: -0.0000

Data Index: 494076 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1240956 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6373. Min Act: -0.0000

Data Index: 652929 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1383487 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1692318 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6726. Min Act: -0.0000

Data Index: 949012 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6078. Min Act: -0.0000

Data Index: 45997 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6262. Min Act: -0.0000

Data Index: 730339 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1201480 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6222. Min Act: -0.0000

Data Index: 637897 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1033172 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1523777 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5926. Min Act: -0.0000

Data Index: 247772 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1099574 (The Pile)

Max Activating Token Index: 91