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

Dataset: The Pile

Neuron 1211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.2577. Min Act: -0.0000

Data Index: 298 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.1420. Min Act: -0.0000

Data Index: 974591 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.1485. Min Act: -0.0000

Data Index: 572718 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1706670 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1579356 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1535873 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1097029 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8675. Min Act: -0.0000

Data Index: 626872 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7358. Min Act: -0.0000

Data Index: 622978 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1191815 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1362256 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1047544 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1524273 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8701. Min Act: -0.0000

Data Index: 10897 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8008. Min Act: -0.0000

Data Index: 228717 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7698. Min Act: -0.0000

Data Index: 542968 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1767984 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1279937 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6908. Min Act: -0.0000

Data Index: 878674 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1815210 (The Pile)

Max Activating Token Index: 146