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

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

Neuron 22 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0003

Data Index: 818884 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 782051 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 845146 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 209570 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1047434 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 328835 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 550398 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 727806 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 301053 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1143900 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0003

Data Index: 355508 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 136662 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0004

Data Index: 484451 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 727669 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 136449 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1061020 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1323173 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 652440 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 638956 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1130617 (C4 (Web Text))

Max Activating Token Index: 25