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

Dataset: The Pile

Neuron 1954 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1036489 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4528. Min Act: -0.0000

Data Index: 168447 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3417. Min Act: -0.0000

Data Index: 396721 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1392867 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2714. Min Act: -0.0000

Data Index: 222420 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3166. Min Act: -0.0000

Data Index: 514242 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3352. Min Act: -0.0000

Data Index: 782145 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2585. Min Act: -0.0000

Data Index: 187834 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1291934 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1591339 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2863. Min Act: -0.0000

Data Index: 156375 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1752014 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1714283 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1637. Min Act: -0.0000

Data Index: 400726 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1407856 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1937331 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1790. Min Act: -0.0000

Data Index: 283195 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1417. Min Act: -0.0000

Data Index: 227678 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1834837 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1438119 (The Pile)

Max Activating Token Index: 820