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

Dataset: The Pile

Neuron 2997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1112871 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4401. Min Act: -0.0000

Data Index: 100729 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3576. Min Act: -0.0000

Data Index: 650940 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4046. Min Act: -0.0000

Data Index: 715809 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4080. Min Act: -0.0000

Data Index: 558284 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1043781 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3475. Min Act: -0.0000

Data Index: 854738 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1795937 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3933. Min Act: -0.0000

Data Index: 362854 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3619. Min Act: -0.0000

Data Index: 594687 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1300252 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1261408 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4103. Min Act: -0.0000

Data Index: 18566 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3642. Min Act: -0.0000

Data Index: 253482 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3388. Min Act: -0.0000

Data Index: 894089 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3518. Min Act: -0.0000

Data Index: 581538 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3791. Min Act: -0.0000

Data Index: 665167 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3720. Min Act: -0.0000

Data Index: 147453 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1850787 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3295. Min Act: -0.0000

Data Index: 831891 (The Pile)

Max Activating Token Index: 842