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

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

Neuron 1269 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1163405 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0922. Min Act: -0.0001

Data Index: 532732 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0936. Min Act: -0.0001

Data Index: 43305 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0852. Min Act: -0.0001

Data Index: 490417 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1280366 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0878. Min Act: -0.0001

Data Index: 716731 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1336664 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1057151 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0829. Min Act: -0.0001

Data Index: 593302 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0841. Min Act: -0.0001

Data Index: 357741 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0805. Min Act: -0.0001

Data Index: 712613 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1291962 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1319275 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0756. Min Act: -0.0001

Data Index: 675667 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0752. Min Act: -0.0001

Data Index: 467446 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0806. Min Act: -0.0001

Data Index: 219414 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0794. Min Act: -0.0001

Data Index: 562614 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0789. Min Act: -0.0001

Data Index: 745713 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1059967 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0698. Min Act: -0.0001

Data Index: 993416 (C4 (Web Text))

Max Activating Token Index: 924