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

Dataset: The Pile

Neuron 1678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4954. Min Act: -0.0000

Data Index: 369254 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1097632 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1380792 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4563. Min Act: -0.0000

Data Index: 218846 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2961. Min Act: -0.0000

Data Index: 350007 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3716. Min Act: -0.0000

Data Index: 751721 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3114. Min Act: -0.0000

Data Index: 43009 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1555565 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1727057 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2871. Min Act: -0.0000

Data Index: 148345 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2496. Min Act: -0.0000

Data Index: 450743 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1730037 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1990668 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1598. Min Act: -0.0000

Data Index: 460512 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2674. Min Act: -0.0000

Data Index: 614802 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1259353 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1293179 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1908488 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1449775 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.0922. Min Act: -0.0000

Data Index: 550062 (The Pile)

Max Activating Token Index: 372