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

Dataset: The Pile

Neuron 1718 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.8187. Min Act: -0.0000

Data Index: 194892 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1130875 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1800662 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1959642 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6592. Min Act: -0.0000

Data Index: 743639 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6548. Min Act: -0.0000

Data Index: 206813 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6724. Min Act: -0.0000

Data Index: 760886 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6837. Min Act: -0.0000

Data Index: 2430 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1644956 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6454. Min Act: -0.0000

Data Index: 513549 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1422233 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1969142 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5870. Min Act: -0.0000

Data Index: 854781 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6195. Min Act: -0.0000

Data Index: 410780 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6039. Min Act: -0.0000

Data Index: 427895 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6088. Min Act: -0.0000

Data Index: 240568 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1550958 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1635432 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1137005 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1002918 (The Pile)

Max Activating Token Index: 112