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

Dataset: The Pile

Neuron 2142 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1507. Min Act: -0.0000

Data Index: 709690 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1481300 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1883175 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9106. Min Act: -0.0000

Data Index: 985889 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8579. Min Act: -0.0001

Data Index: 582223 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1173543 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9219. Min Act: -0.0000

Data Index: 568709 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9030. Min Act: -0.0000

Data Index: 504599 (The Pile)

Max Activating Token Index: 3

Text #8

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1332945 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1495425 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1206867 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8501. Min Act: -0.0000

Data Index: 989401 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1680274 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1748522 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1005832 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1284869 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8198. Min Act: -0.0000

Data Index: 318139 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8676. Min Act: -0.0000

Data Index: 365718 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1232477 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8315. Min Act: -0.0000

Data Index: 927096 (The Pile)

Max Activating Token Index: 524