Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1021828 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3139. Min Act: -0.0000

Data Index: 801463 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3088. Min Act: -0.0000

Data Index: 426681 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1006835 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1338392 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2803. Min Act: -0.0000

Data Index: 896782 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1858067 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2781. Min Act: -0.0000

Data Index: 704863 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1628710 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1713227 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1246226 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1891350 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2560. Min Act: -0.0000

Data Index: 277916 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2434. Min Act: -0.0000

Data Index: 198604 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1458576 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1086234 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2648. Min Act: -0.0000

Data Index: 145863 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2605. Min Act: -0.0000

Data Index: 116909 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1112854 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2541. Min Act: -0.0000

Data Index: 212280 (The Pile)

Max Activating Token Index: 984