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

Dataset: The Pile

Neuron 2230 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1918103 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2364. Min Act: -0.0000

Data Index: 45096 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1044766 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1963445 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1804. Min Act: -0.0000

Data Index: 711518 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1846. Min Act: -0.0000

Data Index: 366227 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1633. Min Act: -0.0000

Data Index: 967422 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1197003 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1490117 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1865769 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1654. Min Act: -0.0000

Data Index: 428535 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1394326 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1885401 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1709. Min Act: -0.0000

Data Index: 209681 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1581820 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1667397 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1754. Min Act: -0.0000

Data Index: 560824 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1615. Min Act: -0.0000

Data Index: 344978 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1694121 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1629. Min Act: -0.0000

Data Index: 102468 (The Pile)

Max Activating Token Index: 607