Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2050. Min Act: -0.0003

Data Index: 1289909 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2010. Min Act: -0.0003

Data Index: 1052914 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2043. Min Act: -0.0003

Data Index: 1493517 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2007. Min Act: -0.0003

Data Index: 1626343 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1984. Min Act: -0.0003

Data Index: 1603929 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2018. Min Act: -0.0003

Data Index: 50968 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2015. Min Act: -0.0003

Data Index: 145842 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2040. Min Act: -0.0003

Data Index: 1381822 (Python Code)

Max Activating Token Index: 1020

Text #8

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2004. Min Act: -0.0003

Data Index: 30488 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2034. Min Act: -0.0003

Data Index: 1575762 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2032. Min Act: -0.0003

Data Index: 1474524 (Python Code)

Max Activating Token Index: 1013

Text #11

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1971. Min Act: -0.0003

Data Index: 558255 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1999. Min Act: -0.0003

Data Index: 1048561 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1987. Min Act: -0.0003

Data Index: 1429177 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1951. Min Act: -0.0003

Data Index: 274621 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1948. Min Act: -0.0003

Data Index: 1577895 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1979. Min Act: -0.0003

Data Index: 1247170 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1941. Min Act: -0.0003

Data Index: 1618800 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1947. Min Act: -0.0003

Data Index: 753151 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1974. Min Act: -0.0003

Data Index: 1140257 (C4 (Web Text))

Max Activating Token Index: 985