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

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

Neuron 2713 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0062. Min Act: -0.0002

Data Index: 99649 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1018119 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0057. Min Act: -0.0002

Data Index: 347981 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0002

Data Index: 819324 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1134894 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1342266 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0002

Data Index: 225967 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 129747 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0002

Data Index: 986640 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 880149 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 672806 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1325748 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 431176 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 421685 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1060486 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 519843 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 402272 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 877750 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 737310 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0002

Data Index: 295938 (C4 (Web Text))

Max Activating Token Index: 439