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

Dataset: The Pile

Neuron 2752 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: 0.8145. Min Range: -0.8145

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1296889 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.8145. Min Act: -0.0000

Data Index: 841496 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1692095 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7745. Min Act: -0.0000

Data Index: 827625 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7618. Min Act: -0.0000

Data Index: 716727 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7733. Min Act: -0.0000

Data Index: 61816 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7388. Min Act: -0.0000

Data Index: 402484 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7283. Min Act: -0.0000

Data Index: 529071 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1256718 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7042. Min Act: -0.0000

Data Index: 676739 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.7814. Min Act: -0.0000

Data Index: 159545 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1891375 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6780. Min Act: -0.0000

Data Index: 743410 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6376. Min Act: 0.0000

Data Index: 804960 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6376. Min Act: -0.0000

Data Index: 806561 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1845150 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1950546 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1414609 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.5901. Min Act: -0.0000

Data Index: 125924 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.5694. Min Act: -0.0000

Data Index: 860229 (The Pile)

Max Activating Token Index: 574