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

Dataset: The Pile

Neuron 980 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6967. Min Range: -8.6967

Max Act: 8.6967. Min Act: -0.0000

Data Index: 975460 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.0190. Min Act: -0.0000

Data Index: 1102365 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 8.6967. Min Range: -8.6967

Max Act: 1.8478. Min Act: -0.0000

Data Index: 300496 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 8.6967. Min Range: -8.6967

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1464178 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1847441 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1234687 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1441195 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.0474. Min Act: -0.0000

Data Index: 3920 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.0227. Min Act: -0.0000

Data Index: 1102358 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1963473 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.4433. Min Act: -0.0000

Data Index: 154787 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.4025. Min Act: -0.0000

Data Index: 33588 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1247418 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.3903. Min Act: -0.0000

Data Index: 776629 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1409553 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.3291. Min Act: -0.0000

Data Index: 924672 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.3157. Min Act: -0.0000

Data Index: 410670 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.3016. Min Act: -0.0000

Data Index: 512540 (The Pile)

Max Activating Token Index: 739

Text #18

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.3510. Min Act: -0.0000

Data Index: 614248 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 8.6967. Min Range: -8.6967

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1064592 (The Pile)

Max Activating Token Index: 758