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

Dataset: The Pile

Neuron 4762 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: 0.5215. Min Range: -0.5215

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1412851 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1233926 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4615. Min Act: -0.0000

Data Index: 383045 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1634131 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4060. Min Act: -0.0000

Data Index: 18369 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1390810 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4770. Min Act: -0.0000

Data Index: 221006 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1498025 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4293. Min Act: -0.0000

Data Index: 82631 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4080. Min Act: -0.0000

Data Index: 260012 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1490372 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1845804 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1880696 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1962863 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3860. Min Act: -0.0000

Data Index: 375216 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3402. Min Act: -0.0000

Data Index: 350814 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4194. Min Act: -0.0000

Data Index: 165953 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1633104 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1647488 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3267. Min Act: -0.0000

Data Index: 506216 (The Pile)

Max Activating Token Index: 752