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

Dataset: The Pile

Neuron 907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.8572. Min Act: -0.0000

Data Index: 1998457 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1106190 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4443. Min Act: -0.0000

Data Index: 773487 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4486. Min Act: -0.0000

Data Index: 509972 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3459. Min Act: -0.0000

Data Index: 670345 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1355204 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3441. Min Act: -0.0000

Data Index: 438171 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1163277 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4440. Min Act: -0.0000

Data Index: 836294 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3519. Min Act: -0.0000

Data Index: 104579 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1918992 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3355. Min Act: -0.0000

Data Index: 384561 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1784741 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1754077 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1224208 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3203. Min Act: -0.0000

Data Index: 848891 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3156. Min Act: -0.0000

Data Index: 923795 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1683298 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2630. Min Act: -0.0000

Data Index: 960269 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3306. Min Act: -0.0000

Data Index: 57310 (The Pile)

Max Activating Token Index: 523