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

Dataset: The Pile

Neuron 1152 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.9392. Min Act: -0.0001

Data Index: 1103010 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 12.0133. Min Range: -12.0133

Max Act: 12.0133. Min Act: -0.0001

Data Index: 1626524 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8724. Min Act: -0.0000

Data Index: 1090372 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8740. Min Act: -0.0000

Data Index: 1973258 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8722. Min Act: -0.0000

Data Index: 1822985 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.9539. Min Act: -0.0000

Data Index: 1902107 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8676. Min Act: -0.0001

Data Index: 327333 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.7838. Min Act: -0.0001

Data Index: 1187327 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.7880. Min Act: -0.0000

Data Index: 1863631 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8703. Min Act: -0.0000

Data Index: 814862 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6972. Min Act: -0.0000

Data Index: 1805407 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8690. Min Act: -0.0000

Data Index: 1057766 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6157. Min Act: -0.0000

Data Index: 118644 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6884. Min Act: -0.0000

Data Index: 61375 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.5213. Min Act: -0.0000

Data Index: 166962 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.7772. Min Act: -0.0001

Data Index: 656475 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6806. Min Act: -0.0001

Data Index: 1694352 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6745. Min Act: -0.0000

Data Index: 806808 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.8516. Min Act: -0.0000

Data Index: 1021032 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 12.0133. Min Range: -12.0133

Max Act: 11.6535. Min Act: -0.0000

Data Index: 1570488 (The Pile)

Max Activating Token Index: 862