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

Dataset: The Pile

Neuron 2445 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: 1.5376. Min Range: -1.5376

Max Act: 1.5376. Min Act: -0.0000

Data Index: 288712 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1937999 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.2026. Min Act: -0.0000

Data Index: 503343 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1779270 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1175850 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1026819 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0957. Min Act: -0.0000

Data Index: 426842 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1529115 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1920769 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9771. Min Act: -0.0000

Data Index: 6895 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0937. Min Act: -0.0000

Data Index: 383961 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9525. Min Act: -0.0000

Data Index: 884938 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1458651 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9450. Min Act: -0.0000

Data Index: 444500 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1019797 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1917668 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1394825 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1482866 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9842. Min Act: -0.0000

Data Index: 308144 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1381992 (The Pile)

Max Activating Token Index: 540