Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1777037 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1416685 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1864287 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6371. Min Act: -0.0000

Data Index: 637726 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1519150 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1440785 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1879263 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1707341 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1506799 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1816298 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1832403 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1908658 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1555694 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6492. Min Act: -0.0000

Data Index: 770403 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6242. Min Act: -0.0000

Data Index: 49373 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5362. Min Act: -0.0000

Data Index: 19925 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1225426 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5517. Min Act: -0.0000

Data Index: 162146 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1872843 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1071914 (The Pile)

Max Activating Token Index: 172