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

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

Neuron 5089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1241705 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2091. Min Act: -0.0001

Data Index: 98136 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2109. Min Act: -0.0001

Data Index: 155330 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2071. Min Act: -0.0001

Data Index: 55367 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1180669 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1902. Min Act: -0.0001

Data Index: 569445 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1796. Min Act: -0.0001

Data Index: 949169 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1932. Min Act: -0.0001

Data Index: 459477 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1868. Min Act: -0.0001

Data Index: 305378 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1090071 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1858. Min Act: -0.0001

Data Index: 869157 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1000471 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1108166 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1892. Min Act: -0.0001

Data Index: 396683 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1238262 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1880. Min Act: -0.0001

Data Index: 940709 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1714. Min Act: -0.0001

Data Index: 784672 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2003. Min Act: -0.0001

Data Index: 911389 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1855. Min Act: -0.0001

Data Index: 893123 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1990. Min Act: -0.0001

Data Index: 33142 (C4 (Web Text))

Max Activating Token Index: 195