Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2029 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0003

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1038. Min Act: -0.0003

Data Index: 1149851 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0978. Min Act: -0.0003

Data Index: 1563385 (Python Code)

Max Activating Token Index: 720

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0977. Min Act: -0.0003

Data Index: 501806 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0967. Min Act: -0.0003

Data Index: 423260 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0837. Min Act: -0.0003

Data Index: 344885 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1051030 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0956. Min Act: -0.0003

Data Index: 1178186 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0937. Min Act: -0.0003

Data Index: 479352 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0923. Min Act: -0.0003

Data Index: 112012 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1282574 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1614728 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0929. Min Act: -0.0003

Data Index: 1352696 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1374204 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0924. Min Act: -0.0003

Data Index: 431074 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0803. Min Act: -0.0003

Data Index: 767266 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0820. Min Act: -0.0003

Data Index: 123439 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1468030 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1170655 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0857. Min Act: -0.0003

Data Index: 281966 (C4 (Web Text))

Max Activating Token Index: 229