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

Dataset: The Pile

Neuron 1753 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: 0.8764. Min Range: -0.8764

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1377820 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1820800 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1556449 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7732. Min Act: -0.0000

Data Index: 845146 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7073. Min Act: -0.0000

Data Index: 561168 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6876. Min Act: -0.0000

Data Index: 457035 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1883138 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1458349 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1677234 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6929. Min Act: -0.0000

Data Index: 228142 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6304. Min Act: -0.0000

Data Index: 281886 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6225. Min Act: -0.0000

Data Index: 260124 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1429721 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6606. Min Act: -0.0000

Data Index: 771984 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1481341 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1612760 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6454. Min Act: -0.0000

Data Index: 326168 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1910419 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6617. Min Act: -0.0000

Data Index: 564653 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5992. Min Act: -0.0000

Data Index: 2422 (The Pile)

Max Activating Token Index: 836