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

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

Neuron 686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0001

Data Index: 754629 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0711. Min Act: -0.0001

Data Index: 627907 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1064395 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1198656 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0794. Min Act: -0.0001

Data Index: 217432 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0793. Min Act: -0.0001

Data Index: 438152 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1218694 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1214234 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0662. Min Act: -0.0001

Data Index: 437729 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0702. Min Act: -0.0001

Data Index: 315798 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0721. Min Act: -0.0001

Data Index: 452908 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0720. Min Act: -0.0001

Data Index: 743490 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1213690 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0759. Min Act: -0.0001

Data Index: 891683 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0682. Min Act: -0.0001

Data Index: 319544 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1059542 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0673. Min Act: -0.0001

Data Index: 709994 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0777. Min Act: -0.0001

Data Index: 664843 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0722. Min Act: -0.0001

Data Index: 933806 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0691. Min Act: -0.0001

Data Index: 167901 (C4 (Web Text))

Max Activating Token Index: 240