Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 773 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0003

Data Index: 1256853 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1172785 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1109946 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0955. Min Act: -0.0003

Data Index: 973159 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0973. Min Act: -0.0003

Data Index: 130154 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1063760 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0931. Min Act: -0.0003

Data Index: 118876 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0925. Min Act: -0.0003

Data Index: 871927 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0902. Min Act: -0.0003

Data Index: 168299 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1135806 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0925. Min Act: -0.0003

Data Index: 627037 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0880. Min Act: -0.0004

Data Index: 1091950 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1316221 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0903. Min Act: -0.0003

Data Index: 214336 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0903. Min Act: -0.0003

Data Index: 683245 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0868. Min Act: -0.0003

Data Index: 800229 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0876. Min Act: -0.0003

Data Index: 620147 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0875. Min Act: -0.0003

Data Index: 118895 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0857. Min Act: -0.0003

Data Index: 934043 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1251433 (C4 (Web Text))

Max Activating Token Index: 209