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

Dataset: The Pile

Neuron 3554 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: 1.7853. Min Range: -1.7853

Max Act: 1.7853. Min Act: -0.0000

Data Index: 298980 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5646. Min Act: -0.0000

Data Index: 1358004 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1745983 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4311. Min Act: -0.0000

Data Index: 763535 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6270. Min Act: -0.0000

Data Index: 870948 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1784048 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3816. Min Act: -0.0000

Data Index: 790307 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1034181 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1301071 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1361580 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3497. Min Act: -0.0000

Data Index: 214977 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.2975. Min Act: -0.0000

Data Index: 609143 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1722962 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.2796. Min Act: -0.0000

Data Index: 565860 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3454. Min Act: -0.0000

Data Index: 147900 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.2827. Min Act: -0.0000

Data Index: 346181 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3346. Min Act: -0.0000

Data Index: 112450 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3055. Min Act: -0.0000

Data Index: 1734256 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.1927. Min Act: -0.0000

Data Index: 603465 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1592230 (The Pile)

Max Activating Token Index: 489