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

Dataset: The Pile

Neuron 4198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9066. Min Range: -1.9066

Max Act: 1.9066. Min Act: -0.0000

Data Index: 1413429 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.9066. Min Range: -1.9066

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1933460 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.9284. Min Act: -0.0000

Data Index: 388080 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1243700 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1856249 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6189. Min Act: -0.0000

Data Index: 68939 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6135. Min Act: -0.0000

Data Index: 595692 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5664. Min Act: -0.0000

Data Index: 733467 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6399. Min Act: -0.0000

Data Index: 864345 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1540158 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.6203. Min Act: -0.0000

Data Index: 853399 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1490619 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5094. Min Act: -0.0000

Data Index: 838043 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1271363 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.4904. Min Act: -0.0000

Data Index: 675454 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5868. Min Act: -0.0000

Data Index: 562006 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1089168 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1849866 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1746392 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 1.9066. Min Range: -1.9066

Max Act: 0.4681. Min Act: -0.0000

Data Index: 971786 (The Pile)

Max Activating Token Index: 470