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

Dataset: The Pile

Neuron 1325 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: 1.2920. Min Range: -1.2920

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1198528 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1131. Min Act: -0.0000

Data Index: 465935 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0588. Min Act: -0.0000

Data Index: 8568 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9527. Min Act: -0.0000

Data Index: 738053 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1157652 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1365. Min Act: -0.0000

Data Index: 310570 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1743780 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1637938 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9374. Min Act: -0.0000

Data Index: 501893 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1752255 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1122727 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0133. Min Act: -0.0000

Data Index: 733073 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9250. Min Act: -0.0000

Data Index: 15996 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1932873 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1108749 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1215691 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8545. Min Act: -0.0000

Data Index: 57313 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1268699 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9226. Min Act: -0.0000

Data Index: 760652 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8739. Min Act: -0.0000

Data Index: 40174 (The Pile)

Max Activating Token Index: 1021