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

Dataset: The Pile

Neuron 2935 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: 0.1067. Min Range: -0.1067

Max Act: 0.1067. Min Act: -0.0000

Data Index: 179071 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1625365 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1634091 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0629. Min Act: -0.0000

Data Index: 86109 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0653. Min Act: -0.0000

Data Index: 696862 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1672841 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1878767 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1226509 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0655. Min Act: -0.0000

Data Index: 194452 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1122255 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0635. Min Act: -0.0000

Data Index: 98376 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1296174 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0565. Min Act: -0.0000

Data Index: 36774 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0561. Min Act: -0.0000

Data Index: 657515 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1990722 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0585. Min Act: -0.0000

Data Index: 362623 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0560. Min Act: -0.0000

Data Index: 776392 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1870143 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0607. Min Act: -0.0000

Data Index: 665441 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1559859 (The Pile)

Max Activating Token Index: 481