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

Dataset: The Pile

Neuron 2421 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1657937 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1278063 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1998574 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3937. Min Act: -0.0000

Data Index: 920 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3623. Min Act: -0.0000

Data Index: 87341 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3793. Min Act: -0.0000

Data Index: 678113 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1702305 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3857. Min Act: -0.0000

Data Index: 862911 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3850. Min Act: -0.0000

Data Index: 175934 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3648. Min Act: -0.0000

Data Index: 141157 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3791. Min Act: -0.0000

Data Index: 662728 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3529. Min Act: -0.0000

Data Index: 808732 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3507. Min Act: -0.0000

Data Index: 349359 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1775 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1925807 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3548. Min Act: -0.0000

Data Index: 264982 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1047934 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3532. Min Act: -0.0000

Data Index: 115253 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3441. Min Act: -0.0000

Data Index: 527401 (The Pile)

Max Activating Token Index: 468