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

Dataset: The Pile

Neuron 5062 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9603. Min Range: -5.9603

Max Act: 5.9603. Min Act: -0.0000

Data Index: 1700364 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 5.9603. Min Range: -5.9603

Max Act: 5.3381. Min Act: -0.0000

Data Index: 1818919 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.7230. Min Act: -0.0000

Data Index: 1354631 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.4412. Min Act: -0.0000

Data Index: 421141 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.7975. Min Act: 0.0000

Data Index: 527427 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.5681. Min Act: 0.0000

Data Index: 1324495 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.8315. Min Act: -0.0000

Data Index: 1149481 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.7936. Min Act: 0.0001

Data Index: 615237 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.1266. Min Act: -0.0000

Data Index: 795544 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.7343. Min Act: -0.0000

Data Index: 1854737 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.7992. Min Act: -0.0000

Data Index: 1811756 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.9591. Min Act: -0.0000

Data Index: 84965 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.6008. Min Act: -0.0000

Data Index: 783163 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 5.9603. Min Range: -5.9603

Max Act: 4.0824. Min Act: -0.0000

Data Index: 539930 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.7446. Min Act: -0.0000

Data Index: 1330067 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.8898. Min Act: -0.0000

Data Index: 956805 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.6353. Min Act: -0.0000

Data Index: 1664792 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.6171. Min Act: -0.0000

Data Index: 629434 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.7525. Min Act: -0.0000

Data Index: 325390 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 5.9603. Min Range: -5.9603

Max Act: 3.8239. Min Act: 0.0000

Data Index: 1947611 (The Pile)

Max Activating Token Index: 191