Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2715. Min Act: -0.0000

Data Index: 411525 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2021. Min Act: -0.0000

Data Index: 554591 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1819447 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1125657 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1787. Min Act: -0.0000

Data Index: 648603 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1375105 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1885989 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1745. Min Act: -0.0000

Data Index: 801686 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1651. Min Act: -0.0000

Data Index: 782940 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1743. Min Act: -0.0000

Data Index: 810429 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1705. Min Act: -0.0000

Data Index: 855410 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1859129 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1932968 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1596. Min Act: -0.0000

Data Index: 452790 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1584209 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1165670 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1766882 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1203659 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1063313 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1672. Min Act: -0.0000

Data Index: 951934 (The Pile)

Max Activating Token Index: 1018