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

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

Neuron 1652 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1124307 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0016. Min Act: -0.0003

Data Index: 242649 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1233623 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0014. Min Act: -0.0004

Data Index: 1315760 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0003

Data Index: 748817 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1436201 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0003

Data Index: 232828 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0004

Data Index: 962551 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0003

Data Index: 949956 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0004

Data Index: 197412 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 711084 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0004

Data Index: 730575 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 423874 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 1525546 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 240910 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0004

Data Index: 1096513 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 1225445 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 1257917 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 874921 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0004

Data Index: 349319 (C4 (Web Text))

Max Activating Token Index: 940