Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.2004. Min Act: -0.0001

Data Index: 653974 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1992. Min Act: -0.0001

Data Index: 851798 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1934. Min Act: -0.0001

Data Index: 80993 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1856. Min Act: -0.0001

Data Index: 744727 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1196389 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1151531 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1106092 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1908. Min Act: -0.0001

Data Index: 294121 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1157170 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1892. Min Act: -0.0001

Data Index: 436420 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1871. Min Act: -0.0001

Data Index: 199296 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1872. Min Act: -0.0001

Data Index: 489447 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1144539 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.2002. Min Act: -0.0001

Data Index: 94215 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1836. Min Act: -0.0001

Data Index: 115083 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1974. Min Act: -0.0001

Data Index: 562943 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1856. Min Act: -0.0001

Data Index: 657036 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1329436 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1231110 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1797. Min Act: -0.0001

Data Index: 441599 (C4 (Web Text))

Max Activating Token Index: 71