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

Dataset: The Pile

Neuron 3385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.3232. Min Act: -0.0000

Data Index: 662058 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1356521 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.2776. Min Act: -0.0000

Data Index: 812788 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1965937 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1701. Min Act: -0.0000

Data Index: 384932 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0036. Min Act: -0.0000

Data Index: 223041 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0477. Min Act: -0.0000

Data Index: 398756 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0842. Min Act: -0.0000

Data Index: 624541 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0029. Min Act: -0.0000

Data Index: 643872 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1218047 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9944. Min Act: -0.0000

Data Index: 644810 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1350615 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0764. Min Act: -0.0000

Data Index: 783125 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1936481 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1396229 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1710652 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1503832 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1482619 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.7370. Min Act: -0.0000

Data Index: 199500 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.6826. Min Act: -0.0000

Data Index: 490472 (The Pile)

Max Activating Token Index: 283