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

Dataset: The Pile

Neuron 985 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1666919 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1642868 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1130104 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.5762. Min Act: -0.0000

Data Index: 744555 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1997765 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.4872. Min Act: -0.0000

Data Index: 277632 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1413039 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3742. Min Act: -0.0000

Data Index: 222616 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1644806 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3412. Min Act: -0.0000

Data Index: 342187 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1093128 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2406. Min Act: -0.0000

Data Index: 184078 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1421887 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1186383 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1044458 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3098. Min Act: -0.0000

Data Index: 912046 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3453. Min Act: -0.0000

Data Index: 409659 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2351. Min Act: -0.0000

Data Index: 869082 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.3227. Min Act: -0.0000

Data Index: 52409 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.6519. Min Range: -1.6519

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1805093 (The Pile)

Max Activating Token Index: 972