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

Dataset: The Pile

Neuron 1992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1607718 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0725. Min Act: -0.0000

Data Index: 916551 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0648. Min Act: -0.0000

Data Index: 498774 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1882152 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0644. Min Act: -0.0000

Data Index: 408284 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1639007 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0623. Min Act: -0.0000

Data Index: 688113 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1025677 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0635. Min Act: -0.0000

Data Index: 893800 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1645910 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0600. Min Act: -0.0000

Data Index: 67103 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1386961 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1798629 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1088484 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1599127 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0587. Min Act: -0.0000

Data Index: 732695 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1123352 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1664435 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1576696 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0576. Min Act: -0.0000

Data Index: 876399 (The Pile)

Max Activating Token Index: 255