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

Dataset: The Pile

Neuron 3525 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: 0.9245. Min Range: -0.9245

Max Act: 0.9245. Min Act: -0.0000

Data Index: 556061 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1108653 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1587788 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1900567 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4982. Min Act: -0.0000

Data Index: 768387 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1547925 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3776. Min Act: -0.0000

Data Index: 279374 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1223905 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3680. Min Act: -0.0000

Data Index: 515307 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4275. Min Act: -0.0000

Data Index: 116003 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4074. Min Act: -0.0000

Data Index: 92582 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1484733 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3912. Min Act: -0.0000

Data Index: 157185 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4047. Min Act: -0.0000

Data Index: 890254 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3843. Min Act: -0.0000

Data Index: 169038 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3995. Min Act: -0.0000

Data Index: 283903 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1499333 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3699. Min Act: -0.0000

Data Index: 293248 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1101901 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.3349. Min Act: -0.0000

Data Index: 522384 (The Pile)

Max Activating Token Index: 687