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

Dataset: The Pile

Neuron 1646 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: 0.9951. Min Range: -0.9951

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1848018 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1025493 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8824. Min Act: -0.0000

Data Index: 557938 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8044. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1743082 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7835. Min Act: -0.0000

Data Index: 560836 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1960658 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1029736 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1913144 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1456466 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7125. Min Act: -0.0000

Data Index: 492280 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1244745 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1133275 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7102. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1352800 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1136737 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1624532 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1066650 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1168719 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6819. Min Act: -0.0000

Data Index: 484166 (The Pile)

Max Activating Token Index: 444