Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 327 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0584. Min Range: -1.0584

Max Act: 1.0584. Min Act: -0.0000

Data Index: 355749 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1963527 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.8701. Min Act: -0.0000

Data Index: 903018 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7196. Min Act: -0.0000

Data Index: 174752 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.8074. Min Act: -0.0000

Data Index: 52841 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.8390. Min Act: -0.0000

Data Index: 683909 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.8292. Min Act: -0.0000

Data Index: 627256 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7635. Min Act: -0.0000

Data Index: 291900 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1656157 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7793. Min Act: -0.0000

Data Index: 172750 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1958390 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1105866 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1614795 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1199815 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1572761 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.6771. Min Act: -0.0000

Data Index: 52096 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.6986. Min Act: -0.0000

Data Index: 469329 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.6477. Min Act: -0.0000

Data Index: 407435 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.7171. Min Act: -0.0000

Data Index: 584990 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.0584. Min Range: -1.0584

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1368366 (The Pile)

Max Activating Token Index: 315