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

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

Neuron 749 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 396741 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 783510 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 213999 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0003

Data Index: 922439 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1091831 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 246689 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 657142 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 160871 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 427726 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1005689 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 607765 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1054562 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 65106 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 295642 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 147651 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1292830 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1630568 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 5489 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 113688 (C4 (Web Text))

Max Activating Token Index: 107