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

Dataset: The Pile

Neuron 2428 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: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1651198 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0713. Min Act: -0.0000

Data Index: 162383 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1759927 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0705. Min Act: -0.0000

Data Index: 981136 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1427287 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1856629 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0626. Min Act: -0.0000

Data Index: 822834 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0621. Min Act: -0.0000

Data Index: 141306 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0549. Min Act: -0.0000

Data Index: 43391 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0565. Min Act: -0.0000

Data Index: 215775 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1753671 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1866934 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0494. Min Act: -0.0000

Data Index: 68844 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1316749 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1520242 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0549. Min Act: -0.0000

Data Index: 662881 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1596425 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1439327 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1848598 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0494. Min Act: -0.0000

Data Index: 169339 (The Pile)

Max Activating Token Index: 522