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

Dataset: The Pile

Neuron 985 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: 1.3850. Min Range: -1.3850

Max Act: 1.3850. Min Act: -0.0000

Data Index: 584566 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.1801. Min Act: -0.0000

Data Index: 354662 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1785103 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.1434. Min Act: -0.0000

Data Index: 681919 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1452816 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1220067 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.0159. Min Act: 0.0000

Data Index: 418902 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1928729 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1308736 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1019397 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9464. Min Act: -0.0000

Data Index: 342287 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8958. Min Act: 0.0000

Data Index: 1532529 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8849. Min Act: -0.0000

Data Index: 846058 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8299. Min Act: -0.0000

Data Index: 945468 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1691010 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8070. Min Act: -0.0000

Data Index: 496783 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1311735 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1318031 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1685440 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8133. Min Act: -0.0000

Data Index: 366598 (The Pile)

Max Activating Token Index: 481