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

Dataset: The Pile

Neuron 903 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1578634 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1902416 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8321. Min Act: -0.0000

Data Index: 875512 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8554. Min Act: -0.0000

Data Index: 94438 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1252524 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7841. Min Act: -0.0000

Data Index: 663238 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8317. Min Act: -0.0000

Data Index: 584080 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8211. Min Act: -0.0000

Data Index: 581886 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1274107 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7424. Min Act: -0.0000

Data Index: 547033 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1111756 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1103377 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1361428 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1850533 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1682920 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6844. Min Act: -0.0000

Data Index: 704493 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7219. Min Act: -0.0000

Data Index: 640179 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7303. Min Act: -0.0000

Data Index: 700805 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1417121 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6755. Min Act: -0.0000

Data Index: 555643 (The Pile)

Max Activating Token Index: 312