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

Dataset: The Pile

Neuron 4533 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: 1.2915. Min Range: -1.2915

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1633153 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.1848. Min Act: -0.0000

Data Index: 962032 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0504. Min Act: -0.0000

Data Index: 710391 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1534766 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.1158. Min Act: -0.0000

Data Index: 769045 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1596582 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1182896 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1176665 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1434082 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1227491 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 1.2915. Min Range: -1.2915

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1599370 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0250. Min Act: -0.0000

Data Index: 988363 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1505779 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 1.2915. Min Range: -1.2915

Max Act: 0.9173. Min Act: -0.0000

Data Index: 313165 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.2915. Min Range: -1.2915

Max Act: 0.9995. Min Act: -0.0000

Data Index: 88654 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0559. Min Act: -0.0000

Data Index: 347847 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1490118 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1296618 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.2915. Min Range: -1.2915

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1336834 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 1.2915. Min Range: -1.2915

Max Act: 0.9450. Min Act: -0.0000

Data Index: 863468 (The Pile)

Max Activating Token Index: 570