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

Dataset: The Pile

Neuron 5053 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: 1.3087. Min Range: -1.3087

Max Act: 1.3087. Min Act: -0.0000

Data Index: 972357 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1615056 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1276041 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1644752 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9266. Min Act: -0.0000

Data Index: 253517 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1697709 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1965391 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8529. Min Act: -0.0000

Data Index: 408147 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1485982 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1528813 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8840. Min Act: -0.0000

Data Index: 240492 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1666191 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8222. Min Act: -0.0000

Data Index: 74906 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.7728. Min Act: -0.0000

Data Index: 584624 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1768446 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1290870 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8031. Min Act: -0.0000

Data Index: 880813 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8225. Min Act: -0.0000

Data Index: 787259 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.7237. Min Act: -0.0000

Data Index: 659820 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1951527 (The Pile)

Max Activating Token Index: 190