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

Dataset: The Pile

Neuron 4159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2814. Min Range: -5.2814

Max Act: 5.2814. Min Act: -0.0000

Data Index: 286405 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 5.2814. Min Range: -5.2814

Max Act: 5.0301. Min Act: -0.0000

Data Index: 884754 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.6823. Min Act: -0.0000

Data Index: 1018356 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 5.2814. Min Range: -5.2814

Max Act: 5.1244. Min Act: -0.0000

Data Index: 1799072 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.8496. Min Act: -0.0000

Data Index: 1969197 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.5567. Min Act: -0.0000

Data Index: 334542 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.7840. Min Act: -0.0000

Data Index: 1787538 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.5486. Min Act: -0.0000

Data Index: 1785545 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.4573. Min Act: -0.0000

Data Index: 1684253 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.7399. Min Act: -0.0000

Data Index: 1000137 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.6198. Min Act: -0.0000

Data Index: 449850 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.5772. Min Act: -0.0000

Data Index: 564907 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.5704. Min Act: -0.0000

Data Index: 1587827 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.3650. Min Act: -0.0000

Data Index: 236253 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.3616. Min Act: -0.0000

Data Index: 1427055 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.4100. Min Act: -0.0000

Data Index: 647923 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.4270. Min Act: -0.0000

Data Index: 870689 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.4364. Min Act: -0.0000

Data Index: 1231156 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.4505. Min Act: -0.0000

Data Index: 845793 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 5.2814. Min Range: -5.2814

Max Act: 4.6001. Min Act: -0.0000

Data Index: 777181 (The Pile)

Max Activating Token Index: 514