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

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

Neuron 5663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1370270 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1639033 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1561721 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 412145 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1643496 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 711660 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1223258 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 768791 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 936730 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1584663 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 11455 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 417539 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 34825 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 482117 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1574687 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 489188 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 257344 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1149855 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 277326 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1103772 (C4 (Web Text))

Max Activating Token Index: 972