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

Dataset: The Pile

Neuron 4799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1451059 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.3107. Min Act: -0.0000

Data Index: 915344 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.4168. Min Act: -0.0000

Data Index: 185903 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1080674 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1590. Min Act: -0.0000

Data Index: 297623 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2224. Min Act: -0.0000

Data Index: 636693 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1494. Min Act: -0.0000

Data Index: 593777 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2904. Min Act: -0.0000

Data Index: 454691 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1498680 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1659. Min Act: -0.0000

Data Index: 663517 (The Pile)

Max Activating Token Index: 664

Text #10

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1655703 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1206. Min Act: -0.0000

Data Index: 146056 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.0862. Min Act: -0.0000

Data Index: 579982 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2601. Min Act: -0.0000

Data Index: 935107 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2004. Min Act: -0.0000

Data Index: 37626 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1439078 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1541. Min Act: -0.0000

Data Index: 717666 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1887. Min Act: -0.0000

Data Index: 291591 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1361. Min Act: -0.0000

Data Index: 513192 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 1.5863. Min Range: -1.5863

Max Act: 1.1550. Min Act: -0.0000

Data Index: 547310 (The Pile)

Max Activating Token Index: 217