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

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

Neuron 789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2689. Min Act: -0.0000

Data Index: 50198 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2482. Min Act: -0.0000

Data Index: 851032 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0000

Data Index: 40159 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1134164 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2308. Min Act: -0.0000

Data Index: 127605 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2308. Min Act: -0.0001

Data Index: 231781 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1059148 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2160. Min Act: -0.0000

Data Index: 872856 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2008. Min Act: -0.0000

Data Index: 334405 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2032. Min Act: -0.0000

Data Index: 41550 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2033. Min Act: -0.0000

Data Index: 587485 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2097. Min Act: -0.0000

Data Index: 895694 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1999. Min Act: -0.0000

Data Index: 505269 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1934. Min Act: -0.0000

Data Index: 169252 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1997. Min Act: -0.0000

Data Index: 184014 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1961. Min Act: -0.0000

Data Index: 116501 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1960. Min Act: -0.0000

Data Index: 570862 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1199144 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1765. Min Act: -0.0000

Data Index: 649729 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1193777 (C4 (Web Text))

Max Activating Token Index: 582