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

Dataset: The Pile

Neuron 3156 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: 0.9648. Min Range: -0.9648

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1812239 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1015011 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1055980 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1930267 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1171261 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6878. Min Act: -0.0000

Data Index: 861407 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6366. Min Act: -0.0000

Data Index: 376215 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6827. Min Act: -0.0000

Data Index: 361287 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1234992 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6305. Min Act: -0.0000

Data Index: 571515 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6666. Min Act: -0.0000

Data Index: 333367 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7012. Min Act: -0.0000

Data Index: 42425 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6396. Min Act: -0.0000

Data Index: 689891 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6454. Min Act: -0.0000

Data Index: 698406 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1640075 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1040362 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1219916 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1310799 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5816. Min Act: -0.0000

Data Index: 330739 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5620. Min Act: -0.0000

Data Index: 590458 (The Pile)

Max Activating Token Index: 330