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

Dataset: The Pile

Neuron 2709 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: 1.5723. Min Range: -1.5723

Max Act: 1.5723. Min Act: -0.0000

Data Index: 817853 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3706. Min Act: 0.0000

Data Index: 882098 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.2955. Min Act: -0.0000

Data Index: 64527 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0609. Min Act: 0.0000

Data Index: 304883 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0582. Min Act: -0.0000

Data Index: 906241 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1434378 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1597160 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9974. Min Act: -0.0000

Data Index: 98353 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9271. Min Act: -0.0000

Data Index: 517503 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9815. Min Act: -0.0000

Data Index: 316098 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9450. Min Act: -0.0000

Data Index: 363394 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1271404 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9357. Min Act: 0.0000

Data Index: 1120545 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9229. Min Act: -0.0000

Data Index: 134638 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8602. Min Act: -0.0000

Data Index: 284269 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1083507 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1773927 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9408. Min Act: -0.0000

Data Index: 732619 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9521. Min Act: -0.0000

Data Index: 954100 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1863766 (The Pile)

Max Activating Token Index: 338