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

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

Neuron 346 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1455. Min Act: -0.0003

Data Index: 783055 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1223. Min Act: -0.0003

Data Index: 237449 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1203. Min Act: -0.0002

Data Index: 235192 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1127. Min Act: -0.0003

Data Index: 1286983 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1002. Min Act: -0.0003

Data Index: 342583 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1096. Min Act: -0.0003

Data Index: 175693 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1270012 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0992. Min Act: -0.0003

Data Index: 1035221 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0967. Min Act: -0.0002

Data Index: 934943 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0965. Min Act: -0.0003

Data Index: 322054 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0911. Min Act: -0.0002

Data Index: 789996 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0875. Min Act: -0.0002

Data Index: 372251 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1355318 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0912. Min Act: -0.0003

Data Index: 1346137 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0913. Min Act: -0.0003

Data Index: 779298 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0927. Min Act: -0.0002

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0895. Min Act: -0.0002

Data Index: 265271 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1016464 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0852. Min Act: -0.0003

Data Index: 969784 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0882. Min Act: -0.0002

Data Index: 609443 (C4 (Web Text))

Max Activating Token Index: 750