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

Dataset: The Pile

Neuron 1330 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: 0.3612. Min Range: -0.3612

Max Act: 0.3612. Min Act: -0.0000

Data Index: 703001 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1933104 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1144021 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2615. Min Act: -0.0000

Data Index: 199903 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1849302 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1692415 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2773. Min Act: -0.0000

Data Index: 924561 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1583910 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2642. Min Act: -0.0000

Data Index: 936121 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1588382 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1493604 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2516. Min Act: 0.0000

Data Index: 643694 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1446901 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2552. Min Act: -0.0000

Data Index: 546423 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2418. Min Act: -0.0000

Data Index: 581726 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2511. Min Act: -0.0000

Data Index: 989597 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1597191 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2354. Min Act: -0.0000

Data Index: 931902 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1633939 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1055774 (The Pile)

Max Activating Token Index: 671