Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1083. Min Act: -0.0001

Data Index: 94839 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1026. Min Act: -0.0001

Data Index: 89005 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1024. Min Act: -0.0001

Data Index: 922470 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1313332 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0834. Min Act: -0.0001

Data Index: 977471 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0655. Min Act: -0.0001

Data Index: 666979 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1182509 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0680. Min Act: -0.0001

Data Index: 133049 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0669. Min Act: -0.0001

Data Index: 711209 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0647. Min Act: -0.0001

Data Index: 894801 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0532. Min Act: -0.0001

Data Index: 894260 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0615. Min Act: -0.0001

Data Index: 39404 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0601. Min Act: -0.0001

Data Index: 643305 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1240424 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0584. Min Act: -0.0001

Data Index: 321060 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0596. Min Act: -0.0001

Data Index: 217660 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0566. Min Act: -0.0001

Data Index: 233334 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1637661 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0531. Min Act: -0.0001

Data Index: 654628 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1002367 (C4 (Web Text))

Max Activating Token Index: 561