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

Dataset: The Pile

Neuron 3460 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: 0.4859. Min Range: -0.4859

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1043955 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4367. Min Act: -0.0000

Data Index: 960864 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4309. Min Act: -0.0000

Data Index: 170127 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1945820 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1929692 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1221615 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1916306 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3181. Min Act: -0.0000

Data Index: 330970 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4064. Min Act: -0.0000

Data Index: 251325 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4439. Min Act: -0.0000

Data Index: 874233 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1008730 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3737. Min Act: -0.0000

Data Index: 452598 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4447. Min Act: -0.0000

Data Index: 414614 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3814. Min Act: -0.0000

Data Index: 479829 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1548565 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4020. Min Act: -0.0000

Data Index: 353859 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3322. Min Act: -0.0000

Data Index: 106053 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1900626 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1230156 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1938588 (The Pile)

Max Activating Token Index: 657