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

Dataset: The Pile

Neuron 4449 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: 1.6923. Min Range: -1.6923

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1299253 (The Pile)

Max Activating Token Index: 599

Text #1

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.6923. Min Act: -0.0000

Data Index: 572578 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1942076 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3373. Min Act: -0.0000

Data Index: 1214566 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1788572 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2744. Min Act: -0.0000

Data Index: 89764 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3265. Min Act: -0.0000

Data Index: 129890 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2439. Min Act: -0.0000

Data Index: 967174 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1397571 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2768. Min Act: -0.0000

Data Index: 752927 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1442538 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3428. Min Act: -0.0000

Data Index: 411678 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1314369 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1039579 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1391704 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1323419 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1027733 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2647. Min Act: -0.0000

Data Index: 779626 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.1143. Min Act: -0.0000

Data Index: 692929 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.1829. Min Act: -0.0000

Data Index: 827734 (The Pile)

Max Activating Token Index: 80