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

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

Neuron 4852 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.5306. Min Act: -0.0000

Data Index: 348621 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1306297 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1324692 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1624995 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1559062 (Python Code)

Max Activating Token Index: 954

Text #5

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1635560 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1597218 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1585782 (Python Code)

Max Activating Token Index: 838

Text #8

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1576589 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1424940 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1552430 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1408786 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1523402 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1582870 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1516341 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1376650 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1538176 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1551338 (Python Code)

Max Activating Token Index: 759

Text #18

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1554805 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1618235 (Python Code)

Max Activating Token Index: 815