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

Dataset: The Pile

Neuron 3985 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.3370. Min Act: -0.0000

Data Index: 1582607 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.2147. Min Act: -0.0000

Data Index: 289468 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.1122. Min Act: -0.0000

Data Index: 702919 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.0641. Min Act: -0.0000

Data Index: 237570 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.0308. Min Act: 0.0000

Data Index: 792582 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1730146 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.9234. Min Act: -0.0000

Data Index: 611749 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8859. Min Act: -0.0000

Data Index: 80852 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.3370. Min Range: -1.3370

Max Act: 1.0180. Min Act: -0.0000

Data Index: 761339 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.9096. Min Act: -0.0000

Data Index: 53869 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1492214 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8637. Min Act: -0.0000

Data Index: 270291 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8438. Min Act: -0.0000

Data Index: 889033 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1100764 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1946504 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1281851 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1945339 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8012. Min Act: -0.0000

Data Index: 87710 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1431789 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.3370. Min Range: -1.3370

Max Act: 0.7740. Min Act: -0.0000

Data Index: 505973 (The Pile)

Max Activating Token Index: 568