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

Dataset: The Pile

Neuron 4704 in Layer 5

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: 1.2361. Min Act: -0.0000

Data Index: 496686 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.2763. Min Act: -0.0000

Data Index: 69779 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1429011 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.2330. Min Act: -0.0000

Data Index: 411837 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0875. Min Act: -0.0000

Data Index: 389908 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1019. Min Act: -0.0000

Data Index: 188291 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0649. Min Act: -0.0000

Data Index: 371011 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1185. Min Act: -0.0000

Data Index: 414661 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1002591 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1350600 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1436513 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1557. Min Act: -0.0000

Data Index: 169783 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1894843 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0040. Min Act: -0.0000

Data Index: 732549 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0619. Min Act: -0.0000

Data Index: 4441 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9791. Min Act: -0.0000

Data Index: 155349 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9699. Min Act: -0.0000

Data Index: 796616 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1127461 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0063. Min Act: -0.0000

Data Index: 497643 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0053. Min Act: -0.0000

Data Index: 931538 (The Pile)

Max Activating Token Index: 302