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

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

Neuron 4899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1125802 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2562. Min Act: -0.0000

Data Index: 82827 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1127384 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2281. Min Act: -0.0000

Data Index: 846435 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1592444 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1169190 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2031. Min Act: -0.0000

Data Index: 134297 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1896. Min Act: -0.0000

Data Index: 696420 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.2081. Min Act: -0.0000

Data Index: 508100 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1723. Min Act: -0.0000

Data Index: 826712 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1476889 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1010083 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1392381 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1950. Min Act: -0.0000

Data Index: 31309 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1925. Min Act: -0.0000

Data Index: 667398 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1834. Min Act: -0.0000

Data Index: 487595 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1599487 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1877. Min Act: -0.0000

Data Index: 668030 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1884. Min Act: -0.0000

Data Index: 8894 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.2716. Min Range: -0.2716

Max Act: 0.1745. Min Act: -0.0000

Data Index: 114886 (C4 (Web Text))

Max Activating Token Index: 306