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

Dataset: The Pile

Neuron 3968 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1966432 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0914. Min Act: -0.0000

Data Index: 789344 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9901. Min Act: -0.0000

Data Index: 39460 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1709925 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1617110 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1194568 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9535. Min Act: -0.0000

Data Index: 896440 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1353479 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1509190 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1266472 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0434. Min Act: -0.0000

Data Index: 947194 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1840877 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1382044 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9621. Min Act: -0.0000

Data Index: 889370 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1996988 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1204190 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1836853 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1706216 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1222176 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1820236 (The Pile)

Max Activating Token Index: 754