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

Dataset: The Pile

Neuron 3642 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1164474 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1356105 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1833111 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7949. Min Act: -0.0000

Data Index: 950327 (The Pile)

Max Activating Token Index: 346

Text #4

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7056. Min Act: -0.0000

Data Index: 17417 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1394617 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1277985 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6416. Min Act: -0.0000

Data Index: 766188 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7430. Min Act: -0.0000

Data Index: 943494 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6927. Min Act: -0.0000

Data Index: 383190 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1512991 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1114284 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1257217 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7150. Min Act: -0.0000

Data Index: 615996 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1380268 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6483. Min Act: -0.0000

Data Index: 850501 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6823. Min Act: -0.0000

Data Index: 125700 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6853. Min Act: -0.0000

Data Index: 754809 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1658234 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6790. Min Act: -0.0000

Data Index: 301960 (The Pile)

Max Activating Token Index: 154