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

Dataset: The Pile

Neuron 4559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0000

Data Index: 811688 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9092. Min Act: -0.0000

Data Index: 883375 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8793. Min Act: -0.0000

Data Index: 793982 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8906. Min Act: -0.0000

Data Index: 387104 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8084. Min Act: -0.0000

Data Index: 508005 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1626388 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8695. Min Act: -0.0000

Data Index: 150805 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1987007 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9042. Min Act: -0.0000

Data Index: 776736 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1753211 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1333777 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7890. Min Act: -0.0000

Data Index: 447135 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1572383 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8434. Min Act: -0.0000

Data Index: 556905 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8342. Min Act: -0.0000

Data Index: 470656 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8866. Min Act: -0.0000

Data Index: 680641 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8395. Min Act: -0.0000

Data Index: 140694 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1537498 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1802258 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1098484 (The Pile)

Max Activating Token Index: 62