Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6497. Min Act: -0.0002

Data Index: 656514 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6479. Min Act: -0.0001

Data Index: 141820 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6623. Min Act: -0.0002

Data Index: 338488 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6387. Min Act: -0.0001

Data Index: 826267 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6285. Min Act: -0.0002

Data Index: 421792 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5935. Min Act: -0.0002

Data Index: 699932 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5790. Min Act: -0.0002

Data Index: 1098594 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1342080 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6101. Min Act: -0.0002

Data Index: 1031453 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6553. Min Act: -0.0002

Data Index: 435279 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5977. Min Act: -0.0002

Data Index: 1268495 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5986. Min Act: -0.0001

Data Index: 322456 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5790. Min Act: -0.0001

Data Index: 277702 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6196. Min Act: -0.0002

Data Index: 135920 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6125. Min Act: -0.0001

Data Index: 334767 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5775. Min Act: -0.0001

Data Index: 4303 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5712. Min Act: -0.0001

Data Index: 357745 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5537. Min Act: -0.0002

Data Index: 236089 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5733. Min Act: -0.0001

Data Index: 666477 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5940. Min Act: -0.0001

Data Index: 995125 (C4 (Web Text))

Max Activating Token Index: 704