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

Dataset: The Pile

Neuron 4191 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: 0.6733. Min Range: -0.6733

Max Act: 0.6733. Min Act: 0.0000

Data Index: 1704001 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6653. Min Act: 0.0000

Data Index: 281464 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1442957 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5527. Min Act: -0.0000

Data Index: 783778 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5507. Min Act: -0.0000

Data Index: 767576 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1961560 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1521868 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1920696 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1707144 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4879. Min Act: -0.0000

Data Index: 449436 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1931466 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1941546 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4924. Min Act: -0.0000

Data Index: 937213 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1759040 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1813020 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4658. Min Act: -0.0000

Data Index: 191161 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4499. Min Act: -0.0000

Data Index: 206938 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4509. Min Act: -0.0000

Data Index: 417966 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4479. Min Act: -0.0000

Data Index: 29284 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4601. Min Act: -0.0000

Data Index: 160220 (The Pile)

Max Activating Token Index: 531