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

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

Neuron 3276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0001

Data Index: 613850 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0783. Min Act: -0.0001

Data Index: 373486 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0670. Min Act: -0.0001

Data Index: 603068 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1186997 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0730. Min Act: -0.0001

Data Index: 10724 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0702. Min Act: -0.0001

Data Index: 863860 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0760. Min Act: -0.0001

Data Index: 439265 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1156681 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0689. Min Act: -0.0001

Data Index: 320404 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0655. Min Act: -0.0001

Data Index: 874057 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0634. Min Act: -0.0001

Data Index: 487460 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0782. Min Act: -0.0001

Data Index: 980061 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0687. Min Act: -0.0001

Data Index: 978358 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0679. Min Act: -0.0001

Data Index: 205534 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0700. Min Act: -0.0001

Data Index: 723164 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0677. Min Act: -0.0001

Data Index: 854756 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0653. Min Act: -0.0001

Data Index: 702099 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0608. Min Act: -0.0001

Data Index: 760537 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0686. Min Act: -0.0002

Data Index: 598432 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0623. Min Act: -0.0001

Data Index: 86424 (C4 (Web Text))

Max Activating Token Index: 253