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

Dataset: The Pile

Neuron 2671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1508288 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2096. Min Act: -0.0000

Data Index: 431299 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2035. Min Act: -0.0000

Data Index: 253059 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1653. Min Act: -0.0000

Data Index: 347412 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1598172 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.2010. Min Act: -0.0000

Data Index: 353025 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1280. Min Act: -0.0000

Data Index: 257069 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1647. Min Act: -0.0000

Data Index: 124859 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1385. Min Act: -0.0000

Data Index: 636791 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9765. Min Act: -0.0000

Data Index: 1496184 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1847671 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1249. Min Act: -0.0000

Data Index: 373702 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0828. Min Act: -0.0000

Data Index: 760344 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1968970 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0568. Min Act: -0.0000

Data Index: 415640 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0889. Min Act: -0.0000

Data Index: 208252 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.1077. Min Act: -0.0000

Data Index: 62515 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1069628 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.3737. Min Range: -1.3737

Max Act: 0.9939. Min Act: -0.0000

Data Index: 47696 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 1.3737. Min Range: -1.3737

Max Act: 1.0109. Min Act: -0.0000

Data Index: 365101 (The Pile)

Max Activating Token Index: 114