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

Dataset: The Pile

Neuron 717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1973035 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1183568 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.0129. Min Act: -0.0000

Data Index: 865513 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9970. Min Act: -0.0000

Data Index: 801758 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.0064. Min Act: -0.0000

Data Index: 255879 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9077. Min Act: -0.0000

Data Index: 583175 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9122. Min Act: -0.0000

Data Index: 684433 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8769. Min Act: -0.0000

Data Index: 275023 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1407598 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8140. Min Act: -0.0000

Data Index: 141696 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1631169 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1297065 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8602. Min Act: -0.0000

Data Index: 834226 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.7575. Min Act: -0.0000

Data Index: 17930 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.7822. Min Act: -0.0000

Data Index: 639622 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.7633. Min Act: -0.0000

Data Index: 189057 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.7859. Min Act: -0.0000

Data Index: 870950 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1382773 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1685211 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1642476 (The Pile)

Max Activating Token Index: 807