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

Dataset: The Pile

Neuron 2645 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: 1.4371. Min Range: -1.4371

Max Act: 1.4371. Min Act: -0.0000

Data Index: 1997034 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1239345 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1952. Min Act: -0.0000

Data Index: 597368 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1815. Min Act: -0.0000

Data Index: 367004 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0208. Min Act: -0.0000

Data Index: 386599 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0779. Min Act: -0.0000

Data Index: 813687 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0648. Min Act: -0.0000

Data Index: 485238 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0615. Min Act: -0.0000

Data Index: 20875 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0596. Min Act: -0.0000

Data Index: 552395 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0430. Min Act: -0.0000

Data Index: 904446 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1375130 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1736032 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0842. Min Act: -0.0000

Data Index: 762213 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0245. Min Act: -0.0000

Data Index: 729646 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1910891 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1790897 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9974. Min Act: -0.0000

Data Index: 239994 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1835969 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1071397 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9895. Min Act: -0.0000

Data Index: 22334 (The Pile)

Max Activating Token Index: 855