Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1485230 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1927. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1638579 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1445287 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1339461 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1339. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1344. Min Act: -0.0000

Data Index: 475072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1363. Min Act: -0.0000

Data Index: 651593 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1219. Min Act: -0.0000

Data Index: 705176 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1619896 (Python Code)

Max Activating Token Index: 951

Text #11

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1116645 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1150. Min Act: -0.0000

Data Index: 259899 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1076. Min Act: -0.0000

Data Index: 995489 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1621860 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1364299 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1095. Min Act: -0.0000

Data Index: 671183 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1542573 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.0969. Min Act: -0.0000

Data Index: 905393 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.2007. Min Range: -0.2007

Max Act: 0.1087. Min Act: -0.0000

Data Index: 614522 (C4 (Web Text))

Max Activating Token Index: 735