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

Dataset: The Pile

Neuron 3219 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: 0.8051. Min Range: -0.8051

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1461267 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.7230. Min Act: -0.0000

Data Index: 986940 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6990. Min Act: -0.0000

Data Index: 24989 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1973868 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1537012 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1862010 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5916. Min Act: -0.0000

Data Index: 981954 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6255. Min Act: 0.0000

Data Index: 106607 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5676. Min Act: -0.0000

Data Index: 762177 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5941. Min Act: -0.0000

Data Index: 473103 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1385785 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1925869 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5994. Min Act: -0.0000

Data Index: 360578 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5640. Min Act: 0.0000

Data Index: 222833 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5488. Min Act: -0.0000

Data Index: 786822 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5551. Min Act: -0.0000

Data Index: 127015 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5703. Min Act: -0.0000

Data Index: 585345 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5875. Min Act: -0.0000

Data Index: 819434 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5353. Min Act: -0.0000

Data Index: 607000 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1098810 (The Pile)

Max Activating Token Index: 315