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

Dataset: The Pile

Neuron 2493 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.9799. Min Act: -0.0000

Data Index: 742100 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.6154. Min Act: -0.0000

Data Index: 898544 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.7887. Min Act: -0.0000

Data Index: 1723188 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.7366. Min Act: -0.0000

Data Index: 398290 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1261975 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1390010 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1630781 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.6214. Min Act: 0.0000

Data Index: 1697764 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.6251. Min Act: -0.0000

Data Index: 614328 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1796555 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.3310. Min Act: -0.0000

Data Index: 577217 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.5426. Min Act: -0.0000

Data Index: 387175 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1926458 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.4839. Min Act: -0.0000

Data Index: 1075612 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.4580. Min Act: -0.0000

Data Index: 660352 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.3736. Min Act: -0.0000

Data Index: 324088 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1880977 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1896291 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1679647 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 1.9799. Min Range: -1.9799

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1459125 (The Pile)

Max Activating Token Index: 88