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

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

Neuron 175 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.4859. Min Act: -0.0001

Data Index: 1304905 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.3016. Min Act: -0.0001

Data Index: 1148114 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.3617. Min Act: -0.0001

Data Index: 66280 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.2543. Min Act: -0.0000

Data Index: 98260 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.3171. Min Act: -0.0001

Data Index: 378918 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.1635. Min Act: -0.0000

Data Index: 271979 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1039082 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0993. Min Act: -0.0000

Data Index: 755862 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.1954. Min Act: -0.0000

Data Index: 431089 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.2006. Min Act: -0.0000

Data Index: 159976 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.1702. Min Act: -0.0000

Data Index: 280020 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1307455 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.1318. Min Act: -0.0001

Data Index: 98530 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0691. Min Act: -0.0001

Data Index: 527962 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0350. Min Act: -0.0000

Data Index: 263847 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0658. Min Act: -0.0000

Data Index: 174736 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0930. Min Act: -0.0001

Data Index: 368486 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.4859. Min Range: -1.4859

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1195845 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.4859. Min Range: -1.4859

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1020081 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.4859. Min Range: -1.4859

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1169157 (C4 (Web Text))

Max Activating Token Index: 883