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

Dataset: The Pile

Neuron 3305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.1315. Min Act: -0.0000

Data Index: 163707 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.0973. Min Act: -0.0000

Data Index: 707987 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9597. Min Act: -0.0000

Data Index: 662161 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9440. Min Act: 0.0000

Data Index: 1275156 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9077. Min Act: -0.0000

Data Index: 968394 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9125. Min Act: 0.0000

Data Index: 1688483 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9040. Min Act: -0.0000

Data Index: 381663 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1926101 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8972. Min Act: -0.0000

Data Index: 993483 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8944. Min Act: -0.0000

Data Index: 320513 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1717597 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8670. Min Act: 0.0000

Data Index: 864422 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1733810 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8541. Min Act: 0.0000

Data Index: 953616 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1537401 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8620. Min Act: -0.0000

Data Index: 261215 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1693967 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1563364 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1571431 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1574045 (The Pile)

Max Activating Token Index: 70