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

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

Neuron 676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0001

Data Index: 849666 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1084. Min Act: -0.0000

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1021741 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1033. Min Act: -0.0001

Data Index: 79224 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1087700 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1324079 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1038. Min Act: -0.0001

Data Index: 973699 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1267665 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1011. Min Act: -0.0000

Data Index: 298557 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0978. Min Act: -0.0001

Data Index: 912816 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1013. Min Act: -0.0000

Data Index: 108063 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1003. Min Act: -0.0001

Data Index: 496769 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0994. Min Act: -0.0000

Data Index: 828872 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0990. Min Act: -0.0000

Data Index: 26632 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0954. Min Act: -0.0000

Data Index: 418918 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1295827 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0985. Min Act: -0.0000

Data Index: 360314 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0984. Min Act: -0.0000

Data Index: 573567 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0981. Min Act: -0.0000

Data Index: 17056 (C4 (Web Text))

Max Activating Token Index: 340