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

Dataset: The Pile

Neuron 1643 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: 1.7243. Min Range: -1.7243

Max Act: 1.7243. Min Act: -0.0000

Data Index: 621566 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.5640. Min Act: -0.0000

Data Index: 984499 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.3193. Min Act: -0.0000

Data Index: 230457 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1870593 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.2268. Min Act: -0.0000

Data Index: 864012 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.2095. Min Act: -0.0000

Data Index: 202546 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1492. Min Act: -0.0000

Data Index: 803095 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1371779 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1010434 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.0328. Min Act: -0.0000

Data Index: 146833 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.0020. Min Act: -0.0000

Data Index: 232602 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1453942 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1684499 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1849766 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.0490. Min Act: -0.0000

Data Index: 339217 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1127. Min Act: -0.0000

Data Index: 19742 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1056. Min Act: -0.0000

Data Index: 982007 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.7243. Min Range: -1.7243

Max Act: 0.9821. Min Act: -0.0000

Data Index: 55004 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 1.7243. Min Range: -1.7243

Max Act: 0.9810. Min Act: -0.0000

Data Index: 635108 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 1.7243. Min Range: -1.7243

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1422559 (The Pile)

Max Activating Token Index: 743