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

Dataset: The Pile

Neuron 1573 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: 1.6303. Min Range: -1.6303

Max Act: 1.6303. Min Act: -0.0000

Data Index: 1882495 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1769226 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1324. Min Act: -0.0000

Data Index: 933353 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9761. Min Act: -0.0000

Data Index: 553889 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1089001 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1421915 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0818. Min Act: -0.0000

Data Index: 315446 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0032. Min Act: -0.0000

Data Index: 871937 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1385667 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0211. Min Act: -0.0000

Data Index: 308511 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9546. Min Act: -0.0000

Data Index: 616781 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1056683 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9840. Min Act: -0.0000

Data Index: 308818 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1506142 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1812790 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9711. Min Act: -0.0000

Data Index: 851775 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1694606 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9023. Min Act: -0.0000

Data Index: 2275 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9776. Min Act: -0.0000

Data Index: 647233 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1582175 (The Pile)

Max Activating Token Index: 144