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

Dataset: The Pile

Neuron 359 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: 3.7695. Min Range: -3.7695

Max Act: 3.5020. Min Act: -0.0000

Data Index: 228871 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.7095. Min Act: -0.0000

Data Index: 1910736 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.7695. Min Act: -0.0000

Data Index: 1394462 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.1774. Min Act: -0.0000

Data Index: 420868 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.9137. Min Act: -0.0000

Data Index: 1550437 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.2685. Min Act: -0.0000

Data Index: 1720153 (The Pile)

Max Activating Token Index: 909

Text #6

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.2691. Min Act: -0.0000

Data Index: 1979713 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.1683. Min Act: -0.0000

Data Index: 1955546 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.0359. Min Act: -0.0000

Data Index: 797483 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.1581. Min Act: -0.0000

Data Index: 765370 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.9740. Min Act: -0.0000

Data Index: 411396 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.2227. Min Act: -0.0000

Data Index: 1293360 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.9502. Min Act: -0.0000

Data Index: 1853622 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.1035. Min Act: -0.0000

Data Index: 550905 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.0592. Min Act: -0.0000

Data Index: 1945014 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.0291. Min Act: -0.0000

Data Index: 278977 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.9176. Min Act: -0.0000

Data Index: 1506379 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.8746. Min Act: -0.0000

Data Index: 805313 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 3.7695. Min Range: -3.7695

Max Act: 2.8373. Min Act: -0.0000

Data Index: 563858 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 3.7695. Min Range: -3.7695

Max Act: 3.1189. Min Act: -0.0000

Data Index: 1382115 (The Pile)

Max Activating Token Index: 679