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

Dataset: The Pile

Neuron 1825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1990483 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6546. Min Act: -0.0000

Data Index: 316399 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1802133 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6936. Min Act: -0.0000

Data Index: 31560 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6447. Min Act: -0.0000

Data Index: 650035 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1494854 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1239995 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6324. Min Act: -0.0000

Data Index: 772898 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1933707 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1780950 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6260. Min Act: -0.0000

Data Index: 964922 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7082. Min Act: -0.0000

Data Index: 200366 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1397396 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6526. Min Act: -0.0000

Data Index: 66358 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6488. Min Act: -0.0000

Data Index: 989355 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5860. Min Act: -0.0000

Data Index: 289741 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5819. Min Act: -0.0000

Data Index: 143548 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1765450 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1064230 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6801. Min Act: -0.0000

Data Index: 176197 (The Pile)

Max Activating Token Index: 566