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

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

Neuron 5008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3562. Min Range: -4.3562

Max Act: 4.0058. Min Act: -0.0000

Data Index: 906148 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 4.3562. Min Range: -4.3562

Max Act: 4.1045. Min Act: -0.0000

Data Index: 10696 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.7127. Min Act: -0.0000

Data Index: 876406 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.8819. Min Act: -0.0000

Data Index: 407021 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 4.3562. Min Range: -4.3562

Max Act: 4.3562. Min Act: -0.0000

Data Index: 731454 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.9887. Min Act: -0.0000

Data Index: 871964 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.4301. Min Act: -0.0000

Data Index: 150939 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.5600. Min Act: -0.0000

Data Index: 243966 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.6819. Min Act: -0.0000

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.6488. Min Act: -0.0000

Data Index: 673298 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.6250. Min Act: -0.0000

Data Index: 1089637 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.9473. Min Act: -0.0000

Data Index: 1212818 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.5970. Min Act: -0.0000

Data Index: 1279622 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.7235. Min Act: -0.0000

Data Index: 421450 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.5639. Min Act: -0.0000

Data Index: 1003951 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.6595. Min Act: -0.0000

Data Index: 769413 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.2930. Min Act: -0.0000

Data Index: 693609 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.2877. Min Act: -0.0000

Data Index: 1058152 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1019191 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 4.3562. Min Range: -4.3562

Max Act: 3.2673. Min Act: -0.0000

Data Index: 1350890 (C4 (Web Text))

Max Activating Token Index: 911