Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5213 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1023. Min Range: -1.1023

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1042069 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.1023. Min Range: -1.1023

Max Act: 1.0929. Min Act: -0.0000

Data Index: 457272 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.1023. Min Range: -1.1023

Max Act: 1.0099. Min Act: 0.0000

Data Index: 687345 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8906. Min Act: -0.0000

Data Index: 285650 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8738. Min Act: -0.0000

Data Index: 509984 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8707. Min Act: -0.0000

Data Index: 946288 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8498. Min Act: 0.0001

Data Index: 1344009 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1197559 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8600. Min Act: -0.0000

Data Index: 131008 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7973. Min Act: -0.0000

Data Index: 722314 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8085. Min Act: -0.0000

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1093418 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7454. Min Act: -0.0000

Data Index: 974173 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1382906 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1329355 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7346. Min Act: 0.0000

Data Index: 395226 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6644. Min Act: -0.0000

Data Index: 814592 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6827. Min Act: 0.0001

Data Index: 961204 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7110. Min Act: -0.0000

Data Index: 573077 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6554. Min Act: -0.0000

Data Index: 764465 (C4 (Web Text))

Max Activating Token Index: 450