Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1249. Min Act: -0.0000

Data Index: 773174 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1228. Min Act: -0.0000

Data Index: 454775 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1917434 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1885427 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1952547 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1460893 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1546047 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0994. Min Act: -0.0000

Data Index: 782996 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0899. Min Act: -0.0000

Data Index: 367702 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0813. Min Act: -0.0000

Data Index: 358361 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0837. Min Act: -0.0000

Data Index: 442233 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1717352 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1934694 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1213737 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0759. Min Act: -0.0000

Data Index: 21548 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1385291 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1843896 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1599597 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1352149 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1238679 (The Pile)

Max Activating Token Index: 976