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

Dataset: The Pile

Neuron 3609 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: 3.9008. Min Range: -3.9008

Max Act: 3.9008. Min Act: -0.0000

Data Index: 945220 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.6515. Min Act: -0.0000

Data Index: 1704622 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.3485. Min Act: -0.0000

Data Index: 265895 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.1967. Min Act: -0.0000

Data Index: 1323219 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.7173. Min Act: -0.0000

Data Index: 353802 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.7937. Min Act: -0.0000

Data Index: 1456700 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.4262. Min Act: -0.0000

Data Index: 955460 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.7949. Min Act: -0.0000

Data Index: 899396 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.4147. Min Act: -0.0000

Data Index: 1616418 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.2591. Min Act: -0.0000

Data Index: 246847 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.8928. Min Act: -0.0000

Data Index: 1213050 (The Pile)

Max Activating Token Index: 706

Text #11

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.2391. Min Act: -0.0000

Data Index: 918525 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.5624. Min Act: -0.0000

Data Index: 437032 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.7646. Min Act: -0.0000

Data Index: 665776 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1622203 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.4699. Min Act: -0.0000

Data Index: 547261 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1476109 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.9004. Min Act: -0.0000

Data Index: 438659 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 3.9008. Min Range: -3.9008

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1156295 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 3.9008. Min Range: -3.9008

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1058236 (The Pile)

Max Activating Token Index: 245