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

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

Neuron 4847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2075. Min Act: -0.0000

Data Index: 125345 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2267. Min Act: -0.0000

Data Index: 36603 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2249. Min Act: -0.0000

Data Index: 203484 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1983. Min Act: -0.0000

Data Index: 532576 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1987. Min Act: -0.0000

Data Index: 338331 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1911. Min Act: -0.0000

Data Index: 279616 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1245239 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1037047 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2136. Min Act: -0.0000

Data Index: 994287 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1990. Min Act: -0.0000

Data Index: 499702 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1174095 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1924. Min Act: -0.0000

Data Index: 509777 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1932. Min Act: -0.0000

Data Index: 7271 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2101. Min Act: -0.0000

Data Index: 505158 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1115478 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1855. Min Act: -0.0000

Data Index: 797166 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2029. Min Act: -0.0000

Data Index: 196647 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2010. Min Act: -0.0000

Data Index: 72366 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2017. Min Act: -0.0000

Data Index: 268795 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1908. Min Act: -0.0000

Data Index: 599132 (C4 (Web Text))

Max Activating Token Index: 751