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

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

Neuron 4395 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.9678. Min Act: -0.0000

Data Index: 674798 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1019961 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.9093. Min Act: -0.0000

Data Index: 268913 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.8564. Min Act: -0.0000

Data Index: 584568 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.8511. Min Act: -0.0000

Data Index: 69687 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.8223. Min Act: -0.0000

Data Index: 1095865 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7046. Min Act: -0.0000

Data Index: 1028830 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.8773. Min Act: -0.0000

Data Index: 955713 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7055. Min Act: -0.0000

Data Index: 342203 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6809. Min Act: -0.0000

Data Index: 612760 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6659. Min Act: -0.0000

Data Index: 736076 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5752. Min Act: -0.0000

Data Index: 270001 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6670. Min Act: -0.0000

Data Index: 127267 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6392. Min Act: -0.0000

Data Index: 779912 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6295. Min Act: -0.0000

Data Index: 568406 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6137. Min Act: -0.0000

Data Index: 460289 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6052. Min Act: -0.0000

Data Index: 9520 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5785. Min Act: -0.0000

Data Index: 185674 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5731. Min Act: -0.0000

Data Index: 877915 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.4629. Min Act: -0.0000

Data Index: 542575 (C4 (Web Text))

Max Activating Token Index: 665