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

Dataset: The Pile

Neuron 506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 870988 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1842. Min Act: -0.0000

Data Index: 455185 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1332656 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1041915 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1730. Min Act: -0.0000

Data Index: 38807 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1699. Min Act: -0.0000

Data Index: 711962 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1944. Min Act: -0.0000

Data Index: 309461 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1315424 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1170435 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1027890 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1396200 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1041174 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1301724 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1770. Min Act: -0.0000

Data Index: 92774 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1811862 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1541. Min Act: -0.0000

Data Index: 728822 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1564. Min Act: -0.0000

Data Index: 235822 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1541. Min Act: -0.0000

Data Index: 572367 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1484609 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1666064 (The Pile)

Max Activating Token Index: 773