Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3284 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1082. Min Act: -0.0001

Data Index: 420370 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1563886 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1014795 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1626215 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1656786 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1482329 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1636777 (Python Code)

Max Activating Token Index: 369

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0945. Min Act: -0.0001

Data Index: 612469 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1353012 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1574130 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0894. Min Act: -0.0001

Data Index: 801600 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0882. Min Act: -0.0001

Data Index: 155969 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0934. Min Act: -0.0001

Data Index: 774609 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0919. Min Act: -0.0001

Data Index: 861845 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0933. Min Act: -0.0001

Data Index: 917224 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1454663 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0855. Min Act: -0.0001

Data Index: 355492 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1466744 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1126974 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1211016 (C4 (Web Text))

Max Activating Token Index: 218