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

Dataset: The Pile

Neuron 2024 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: 1.9407. Min Range: -1.9407

Max Act: 1.8678. Min Act: -0.0000

Data Index: 1029875 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.8795. Min Act: -0.0000

Data Index: 958165 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.6581. Min Act: -0.0000

Data Index: 153622 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.8494. Min Act: -0.0000

Data Index: 1297557 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1725652 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.7744. Min Act: -0.0000

Data Index: 1374124 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.6732. Min Act: -0.0000

Data Index: 632131 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.6734. Min Act: -0.0000

Data Index: 1427707 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.5996. Min Act: -0.0000

Data Index: 876148 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1679788 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.7311. Min Act: -0.0000

Data Index: 722602 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.6793. Min Act: -0.0000

Data Index: 1863484 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.6086. Min Act: -0.0000

Data Index: 514418 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1056850 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.8247. Min Act: -0.0000

Data Index: 118526 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1829305 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.5833. Min Act: -0.0000

Data Index: 976829 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.7853. Min Act: -0.0000

Data Index: 413745 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1342355 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 1.9407. Min Range: -1.9407

Max Act: 1.7842. Min Act: -0.0000

Data Index: 1153445 (The Pile)

Max Activating Token Index: 372