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

Dataset: The Pile

Neuron 3537 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.5572. Min Act: -0.0000

Data Index: 1260922 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.8619. Min Act: -0.0000

Data Index: 993616 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.1803. Min Act: -0.0000

Data Index: 1539209 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.7336. Min Act: -0.0000

Data Index: 682676 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.9014. Min Act: -0.0000

Data Index: 1335926 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.7126. Min Act: -0.0000

Data Index: 1492825 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.2482. Min Act: -0.0000

Data Index: 437301 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.1502. Min Act: -0.0000

Data Index: 16467 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.2974. Min Act: -0.0000

Data Index: 1875291 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.9028. Min Act: -0.0000

Data Index: 1599332 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.0892. Min Act: -0.0000

Data Index: 131838 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.0826. Min Act: -0.0000

Data Index: 1601119 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.2465. Min Act: -0.0000

Data Index: 821733 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.3033. Min Act: -0.0000

Data Index: 411330 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.5922. Min Act: -0.0000

Data Index: 1592837 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.5939. Min Act: -0.0000

Data Index: 76805 (The Pile)

Max Activating Token Index: 689

Text #16

Max Range: 9.9014. Min Range: -9.9014

Max Act: 9.0440. Min Act: -0.0000

Data Index: 336947 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.5056. Min Act: -0.0000

Data Index: 197227 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.7513. Min Act: -0.0000

Data Index: 980069 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 9.9014. Min Range: -9.9014

Max Act: 8.3463. Min Act: -0.0000

Data Index: 127600 (The Pile)

Max Activating Token Index: 521