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

Dataset: The Pile

Neuron 1715 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: 1.0534. Min Range: -1.0534

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1446662 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 1.0534. Min Range: -1.0534

Max Act: 1.0518. Min Act: -0.0000

Data Index: 568314 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 1.0534. Min Range: -1.0534

Max Act: 1.0534. Min Act: -0.0000

Data Index: 632480 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7958. Min Act: -0.0000

Data Index: 233597 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.9505. Min Act: -0.0000

Data Index: 989916 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1655422 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8771. Min Act: -0.0000

Data Index: 538608 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 1.0534. Min Range: -1.0534

Max Act: 1.0215. Min Act: -0.0000

Data Index: 960747 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.9297. Min Act: -0.0000

Data Index: 332705 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1974039 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1462792 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.9037. Min Act: -0.0000

Data Index: 963708 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1157849 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8424. Min Act: -0.0000

Data Index: 320709 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8231. Min Act: -0.0000

Data Index: 546308 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1016913 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8279. Min Act: -0.0000

Data Index: 422157 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1977031 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8556. Min Act: -0.0000

Data Index: 628378 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1727721 (The Pile)

Max Activating Token Index: 758