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

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

Neuron 875 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5632. Min Act: -0.0000

Data Index: 429514 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1228506 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5563. Min Act: -0.0000

Data Index: 374035 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5406. Min Act: -0.0000

Data Index: 98738 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5257. Min Act: -0.0000

Data Index: 605707 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5340. Min Act: -0.0000

Data Index: 666110 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5102. Min Act: -0.0000

Data Index: 249922 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1012195 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1275754 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4762. Min Act: -0.0000

Data Index: 914619 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4700. Min Act: -0.0000

Data Index: 551233 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1352974 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1160657 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4614. Min Act: -0.0000

Data Index: 833928 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4661. Min Act: -0.0000

Data Index: 668960 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4486. Min Act: -0.0000

Data Index: 327457 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4472. Min Act: -0.0000

Data Index: 664177 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4376. Min Act: -0.0000

Data Index: 614577 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1276165 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.5991. Min Range: -0.5991

Max Act: 0.4322. Min Act: -0.0000

Data Index: 837559 (C4 (Web Text))

Max Activating Token Index: 98