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

Dataset: The Pile

Neuron 2184 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: 1.3710. Min Range: -1.3710

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1509797 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1906367 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2188. Min Act: -0.0000

Data Index: 399081 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1686. Min Act: -0.0000

Data Index: 660650 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2014. Min Act: -0.0000

Data Index: 1003664 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1580. Min Act: -0.0000

Data Index: 290735 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0368. Min Act: -0.0000

Data Index: 270994 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0419. Min Act: -0.0000

Data Index: 718969 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1775123 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9746. Min Act: -0.0000

Data Index: 501091 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1183931 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1059464 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1251429 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1124206 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1702148 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9851. Min Act: -0.0000

Data Index: 499062 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9465. Min Act: -0.0000

Data Index: 512561 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9524. Min Act: -0.0001

Data Index: 138758 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9670. Min Act: -0.0000

Data Index: 27383 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9492. Min Act: -0.0000

Data Index: 768996 (The Pile)

Max Activating Token Index: 96