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

Dataset: The Pile

Neuron 1467 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: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1309959 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1630889 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5954. Min Act: 0.0000

Data Index: 128773 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1340100 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5852. Min Act: 0.0000

Data Index: 942706 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5438. Min Act: -0.0000

Data Index: 781699 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5375. Min Act: -0.0000

Data Index: 519350 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1794733 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5351. Min Act: -0.0000

Data Index: 905106 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4730. Min Act: -0.0000

Data Index: 727748 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1903471 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4964. Min Act: -0.0000

Data Index: 343333 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4599. Min Act: -0.0000

Data Index: 277515 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5165. Min Act: -0.0000

Data Index: 250338 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1567182 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4878. Min Act: -0.0000

Data Index: 198964 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4571. Min Act: -0.0000

Data Index: 243296 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4317. Min Act: -0.0000

Data Index: 843923 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1168885 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1205206 (The Pile)

Max Activating Token Index: 440