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

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

Neuron 361 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0564. Min Act: -0.0003

Data Index: 477117 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 404005 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 618411 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 1262410 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0003

Data Index: 1008995 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 56645 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0003

Data Index: 490373 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0003

Data Index: 670615 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 273763 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0003

Data Index: 1222617 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 349366 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 1143328 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0418. Min Act: -0.0002

Data Index: 864671 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0003

Data Index: 1622105 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0002

Data Index: 1404113 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0003

Data Index: 101776 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0003

Data Index: 213662 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0002

Data Index: 456222 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0003

Data Index: 329688 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0417. Min Act: -0.0003

Data Index: 85983 (C4 (Web Text))

Max Activating Token Index: 1