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

Dataset: The Pile

Neuron 3073 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: 1.4812. Min Range: -1.4812

Max Act: 1.4812. Min Act: -0.0000

Data Index: 910293 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2806. Min Act: -0.0000

Data Index: 1904913 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1546922 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1126952 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2109. Min Act: -0.0000

Data Index: 753968 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0509. Min Act: -0.0000

Data Index: 487437 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0555. Min Act: -0.0000

Data Index: 267638 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1040172 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.9860. Min Act: -0.0000

Data Index: 984384 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.9136. Min Act: -0.0000

Data Index: 945043 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0002. Min Act: -0.0000

Data Index: 705469 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.9050. Min Act: -0.0000

Data Index: 747653 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8516. Min Act: -0.0000

Data Index: 569400 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1582555 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1406102 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1624908 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8419. Min Act: -0.0000

Data Index: 193008 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1507923 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8135. Min Act: -0.0000

Data Index: 152802 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1388226 (The Pile)

Max Activating Token Index: 233