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

Dataset: The Pile

Neuron 4748 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: 0.4187. Min Range: -0.4187

Max Act: 0.4187. Min Act: -0.0000

Data Index: 27393 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3466. Min Act: -0.0000

Data Index: 955904 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3305. Min Act: -0.0000

Data Index: 965088 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3587. Min Act: -0.0000

Data Index: 625743 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1777652 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1708594 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2735. Min Act: -0.0000

Data Index: 720749 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3210. Min Act: -0.0000

Data Index: 968780 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3064. Min Act: -0.0000

Data Index: 361906 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2685. Min Act: -0.0000

Data Index: 128782 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1830713 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2755. Min Act: -0.0000

Data Index: 455150 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2861. Min Act: -0.0000

Data Index: 441794 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2841. Min Act: -0.0000

Data Index: 223131 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1247190 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1193435 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1238611 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2673. Min Act: -0.0000

Data Index: 670297 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2709. Min Act: -0.0000

Data Index: 587586 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2721. Min Act: -0.0000

Data Index: 160299 (The Pile)

Max Activating Token Index: 686