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

Dataset: The Pile

Neuron 20 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: 0.4801. Min Range: -0.4801

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1589844 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.4781. Min Act: -0.0000

Data Index: 927527 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1861111 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1014472 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3791. Min Act: -0.0000

Data Index: 754695 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3930. Min Act: -0.0000

Data Index: 633101 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3800. Min Act: -0.0000

Data Index: 172832 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3793. Min Act: -0.0000

Data Index: 475927 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1723981 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.4000. Min Act: -0.0000

Data Index: 135358 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1587605 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3690. Min Act: -0.0000

Data Index: 562283 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3415. Min Act: -0.0000

Data Index: 813005 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3601. Min Act: -0.0000

Data Index: 79012 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3635. Min Act: -0.0000

Data Index: 877347 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3555. Min Act: -0.0000

Data Index: 98143 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1488608 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1941321 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3531. Min Act: -0.0000

Data Index: 651676 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1295281 (The Pile)

Max Activating Token Index: 555