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

Dataset: The Pile

Neuron 604 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: 1.5260. Min Range: -1.5260

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1599727 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.5260. Min Act: -0.0000

Data Index: 766600 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1367988 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4653. Min Act: -0.0000

Data Index: 1324189 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4832. Min Act: -0.0000

Data Index: 393208 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1585671 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4418. Min Act: -0.0000

Data Index: 1689572 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1463865 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.3972. Min Act: -0.0000

Data Index: 414743 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1666999 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1784793 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2903. Min Act: -0.0000

Data Index: 599195 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1122425 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1370. Min Act: -0.0000

Data Index: 276011 (The Pile)

Max Activating Token Index: 515

Text #14

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2035. Min Act: -0.0000

Data Index: 886538 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1232491 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1572299 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1171357 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1690459 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1921. Min Act: -0.0000

Data Index: 673339 (The Pile)

Max Activating Token Index: 436