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

Dataset: The Pile

Neuron 4652 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: 1.6595. Min Range: -1.6595

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1314695 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1461168 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.2667. Min Act: -0.0000

Data Index: 295846 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1590409 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1114248 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1476941 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1630038 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.1815. Min Act: -0.0000

Data Index: 153584 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.1523. Min Act: -0.0000

Data Index: 303182 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1230799 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0810. Min Act: -0.0000

Data Index: 399385 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0547. Min Act: -0.0000

Data Index: 982117 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0951. Min Act: -0.0000

Data Index: 830135 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1081494 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1049275 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.6595. Min Range: -1.6595

Max Act: 1.0007. Min Act: -0.0000

Data Index: 849399 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 1.6595. Min Range: -1.6595

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1551721 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.6595. Min Range: -1.6595

Max Act: 0.9877. Min Act: -0.0000

Data Index: 546453 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 1.6595. Min Range: -1.6595

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1921374 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.6595. Min Range: -1.6595

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1584924 (The Pile)

Max Activating Token Index: 171