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

Dataset: The Pile

Neuron 594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.1821. Min Act: -0.0000

Data Index: 156812 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9481. Min Act: -0.0000

Data Index: 367548 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.8918. Min Act: -0.0000

Data Index: 426683 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1489538 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1650727 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7173. Min Act: 0.0000

Data Index: 369902 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1847177 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1381012 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.7389. Min Act: -0.0000

Data Index: 825004 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1711328 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6766. Min Act: -0.0000

Data Index: 58789 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1042176 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6649. Min Act: -0.0000

Data Index: 382510 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1667103 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1529723 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.5986. Min Act: -0.0000

Data Index: 33690 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1237283 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1762772 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1724281 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1710902 (The Pile)

Max Activating Token Index: 46