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

Dataset: The Pile

Neuron 1314 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: 1.2322. Min Range: -1.2322

Max Act: 1.2291. Min Act: -0.0000

Data Index: 414132 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1620674 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0796. Min Act: -0.0000

Data Index: 931868 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0056. Min Act: -0.0000

Data Index: 945137 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9427. Min Act: -0.0000

Data Index: 251870 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1968774 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1511048 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1599734 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1558472 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0142. Min Act: -0.0000

Data Index: 693060 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1452669 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1707434 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9619. Min Act: -0.0000

Data Index: 553268 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.8452. Min Act: -0.0000

Data Index: 929502 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1381064 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0029. Min Act: -0.0001

Data Index: 442525 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0399. Min Act: -0.0000

Data Index: 183667 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9752. Min Act: -0.0000

Data Index: 182663 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9731. Min Act: -0.0000

Data Index: 761549 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9701. Min Act: -0.0000

Data Index: 624272 (The Pile)

Max Activating Token Index: 507