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

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

Neuron 2837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1518905 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1409930 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1301422 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1561167 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0917. Min Act: -0.0001

Data Index: 160007 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1137307 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0869. Min Act: -0.0001

Data Index: 480716 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0889. Min Act: -0.0001

Data Index: 847012 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0811. Min Act: -0.0001

Data Index: 448064 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1290250 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1198922 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0795. Min Act: -0.0001

Data Index: 560326 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0853. Min Act: -0.0001

Data Index: 625618 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1508054 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0734. Min Act: -0.0001

Data Index: 805211 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1026558 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0733. Min Act: -0.0001

Data Index: 876194 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1144949 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1171003 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0717. Min Act: -0.0001

Data Index: 654466 (C4 (Web Text))

Max Activating Token Index: 685