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

Dataset: The Pile

Neuron 4562 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6742. Min Act: -0.0000

Data Index: 804552 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1441425 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6454. Min Act: -0.0000

Data Index: 729686 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6812. Min Act: -0.0000

Data Index: 307859 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6465. Min Act: -0.0000

Data Index: 375697 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6354. Min Act: -0.0000

Data Index: 949717 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6310. Min Act: -0.0000

Data Index: 627175 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5958. Min Act: -0.0000

Data Index: 855489 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1485917 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6169. Min Act: -0.0000

Data Index: 200441 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1253202 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5548. Min Act: -0.0000

Data Index: 714522 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1889279 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5677. Min Act: -0.0000

Data Index: 490321 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5339. Min Act: -0.0000

Data Index: 135371 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1031630 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1795980 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5661. Min Act: -0.0000

Data Index: 952924 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1377007 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6001. Min Act: -0.0000

Data Index: 454515 (The Pile)

Max Activating Token Index: 816