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

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

Neuron 1456 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2519. Min Act: -0.0000

Data Index: 78364 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2186. Min Act: -0.0000

Data Index: 395149 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2062. Min Act: -0.0000

Data Index: 489983 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2045. Min Act: 0.0000

Data Index: 1082512 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2158. Min Act: -0.0000

Data Index: 884899 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1015852 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2055. Min Act: -0.0000

Data Index: 637425 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1013718 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2121. Min Act: -0.0000

Data Index: 888701 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1969. Min Act: -0.0000

Data Index: 430565 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2021. Min Act: -0.0000

Data Index: 620829 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1971. Min Act: 0.0001

Data Index: 1204450 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2072. Min Act: 0.0000

Data Index: 1161021 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1987. Min Act: -0.0000

Data Index: 30443 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1926. Min Act: -0.0000

Data Index: 822697 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1994. Min Act: -0.0000

Data Index: 544514 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1980. Min Act: -0.0000

Data Index: 81203 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1308396 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1900. Min Act: -0.0000

Data Index: 539677 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.1891. Min Act: 0.0001

Data Index: 259645 (C4 (Web Text))

Max Activating Token Index: 108