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

Dataset: The Pile

Neuron 803 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: 0.8028. Min Range: -0.8028

Max Act: 0.7809. Min Act: -0.0000

Data Index: 295670 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1841516 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1685661 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6879. Min Act: -0.0000

Data Index: 668588 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.7110. Min Act: -0.0000

Data Index: 277627 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6815. Min Act: -0.0000

Data Index: 477104 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.7237. Min Act: -0.0000

Data Index: 448187 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6912. Min Act: -0.0000

Data Index: 858210 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1442178 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6959. Min Act: -0.0000

Data Index: 515845 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1222652 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1674691 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1932599 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6538. Min Act: -0.0000

Data Index: 833033 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1784713 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1279289 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1011543 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1353764 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6593. Min Act: -0.0000

Data Index: 335731 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6389. Min Act: -0.0000

Data Index: 28432 (The Pile)

Max Activating Token Index: 290