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

Dataset: The Pile

Neuron 1256 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: 1.8729. Min Range: -1.8729

Max Act: 1.6404. Min Act: -0.0000

Data Index: 714156 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1228062 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5689. Min Act: -0.0000

Data Index: 140465 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6160. Min Act: -0.0000

Data Index: 1080230 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6800. Min Act: -0.0000

Data Index: 107735 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.8729. Min Act: -0.0000

Data Index: 26888 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1760608 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5751. Min Act: -0.0000

Data Index: 1474488 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1139890 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4330. Min Act: -0.0000

Data Index: 183505 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4766. Min Act: -0.0000

Data Index: 894629 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5428. Min Act: -0.0000

Data Index: 676852 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1371920 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1625851 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4004. Min Act: -0.0000

Data Index: 957909 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1869853 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1595087 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6416. Min Act: -0.0000

Data Index: 354496 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4625. Min Act: -0.0000

Data Index: 606064 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4963. Min Act: -0.0000

Data Index: 23348 (The Pile)

Max Activating Token Index: 928