Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 848 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4785. Min Act: -0.0000

Data Index: 762543 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1029639 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3985. Min Act: -0.0000

Data Index: 890577 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3989. Min Act: -0.0000

Data Index: 422263 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3974. Min Act: -0.0000

Data Index: 388070 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1581643 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4319. Min Act: -0.0000

Data Index: 475634 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3849. Min Act: -0.0000

Data Index: 189522 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3825. Min Act: -0.0000

Data Index: 573094 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1158137 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3939. Min Act: -0.0000

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3813. Min Act: -0.0000

Data Index: 366463 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3791. Min Act: -0.0000

Data Index: 124672 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3591. Min Act: -0.0000

Data Index: 48494 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3443. Min Act: -0.0000

Data Index: 983255 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1521734 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1639749 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3328. Min Act: -0.0000

Data Index: 869489 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1112253 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3546. Min Act: -0.0000

Data Index: 926599 (C4 (Web Text))

Max Activating Token Index: 378