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

Dataset: The Pile

Neuron 293 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: 1.5373. Min Range: -1.5373

Max Act: 1.4606. Min Act: -0.0000

Data Index: 1717591 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1224259 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1062045 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5153. Min Act: -0.0000

Data Index: 206324 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1442626 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1677060 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1215313 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1260909 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5290. Min Act: -0.0000

Data Index: 719396 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3210. Min Act: -0.0000

Data Index: 452494 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1170671 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1471398 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2374. Min Act: -0.0000

Data Index: 173915 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2098. Min Act: -0.0000

Data Index: 662392 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1829. Min Act: -0.0000

Data Index: 671896 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1605692 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1710639 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3519. Min Act: -0.0000

Data Index: 176130 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3097. Min Act: -0.0000

Data Index: 732336 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2215. Min Act: -0.0000

Data Index: 772354 (The Pile)

Max Activating Token Index: 307