Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1540051 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.1587. Min Act: -0.0000

Data Index: 597992 (The Pile)

Max Activating Token Index: 546

Text #2

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1861657 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.5410. Min Act: -0.0000

Data Index: 288789 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1172133 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1556637 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1125847 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1927479 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1184877 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.9185. Min Act: -0.0000

Data Index: 897150 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.1750. Min Act: -0.0000

Data Index: 228721 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0992. Min Act: -0.0000

Data Index: 278699 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1487311 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.1630. Min Act: -0.0000

Data Index: 255737 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1447639 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0736. Min Act: -0.0000

Data Index: 636013 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1730288 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 1.5410. Min Range: -1.5410

Max Act: 1.0210. Min Act: -0.0000

Data Index: 285763 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.9328. Min Act: -0.0000

Data Index: 626861 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 1.5410. Min Range: -1.5410

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1036555 (The Pile)

Max Activating Token Index: 622