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

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

Neuron 1562 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: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0002

Data Index: 581443 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0121. Min Act: -0.0002

Data Index: 699916 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0002

Data Index: 228100 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0113. Min Act: -0.0002

Data Index: 915972 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0102. Min Act: -0.0002

Data Index: 414386 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0102. Min Act: -0.0002

Data Index: 618982 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0101. Min Act: -0.0002

Data Index: 837608 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0097. Min Act: -0.0002

Data Index: 248058 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0097. Min Act: -0.0002

Data Index: 980364 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0099. Min Act: -0.0002

Data Index: 119264 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0093. Min Act: -0.0002

Data Index: 683815 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0002

Data Index: 748565 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0002

Data Index: 601019 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0002

Data Index: 936889 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0093. Min Act: -0.0002

Data Index: 727450 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0002

Data Index: 626818 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1281896 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0094. Min Act: -0.0002

Data Index: 15210 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 7605 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 969068 (C4 (Web Text))

Max Activating Token Index: 2