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

Dataset: The Pile

Neuron 1696 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1866765 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1707843 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1063599 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1028575 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1358053 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1587288 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1197554 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6795. Min Act: -0.0000

Data Index: 989173 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1237799 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6014. Min Act: -0.0000

Data Index: 528430 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1489318 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6833. Min Act: -0.0000

Data Index: 46756 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1568818 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1846669 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1353545 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1356980 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5704. Min Act: -0.0000

Data Index: 169034 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6009. Min Act: -0.0000

Data Index: 796319 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1067250 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1940295 (The Pile)

Max Activating Token Index: 644