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

Dataset: The Pile

Neuron 1963 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.9982. Min Act: -0.0000

Data Index: 512009 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 7.1399. Min Range: -7.1399

Max Act: 7.1399. Min Act: -0.0000

Data Index: 1256133 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.7233. Min Act: -0.0000

Data Index: 187961 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.7500. Min Act: -0.0000

Data Index: 1192687 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.8926. Min Act: -0.0000

Data Index: 6306 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.7483. Min Act: -0.0000

Data Index: 1249714 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.7748. Min Act: -0.0000

Data Index: 373761 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.5490. Min Act: -0.0000

Data Index: 1045635 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.0277. Min Act: -0.0000

Data Index: 1639788 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 7.1399. Min Range: -7.1399

Max Act: 5.9420. Min Act: -0.0000

Data Index: 467664 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.4383. Min Act: -0.0000

Data Index: 1684565 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.5404. Min Act: -0.0000

Data Index: 489809 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 7.1399. Min Range: -7.1399

Max Act: 5.9894. Min Act: -0.0000

Data Index: 1061612 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 7.1399. Min Range: -7.1399

Max Act: 5.9634. Min Act: -0.0000

Data Index: 1806914 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 7.1399. Min Range: -7.1399

Max Act: 5.9162. Min Act: -0.0000

Data Index: 1893764 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.0968. Min Act: -0.0000

Data Index: 1161639 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.4042. Min Act: -0.0000

Data Index: 1727570 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.1561. Min Act: -0.0000

Data Index: 1216040 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.3935. Min Act: -0.0000

Data Index: 620872 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 7.1399. Min Range: -7.1399

Max Act: 6.1618. Min Act: -0.0000

Data Index: 49783 (The Pile)

Max Activating Token Index: 667