Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0001

Data Index: 209892 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1051984 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0877. Min Act: -0.0001

Data Index: 318655 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1037224 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0829. Min Act: -0.0001

Data Index: 553013 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0893. Min Act: -0.0001

Data Index: 351810 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0832. Min Act: -0.0000

Data Index: 643625 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0887. Min Act: -0.0001

Data Index: 608507 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1156617 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0812. Min Act: -0.0001

Data Index: 652311 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0803. Min Act: -0.0001

Data Index: 133000 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1200892 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1069445 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1345574 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1132521 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0819. Min Act: -0.0001

Data Index: 126113 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1262599 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0804. Min Act: -0.0001

Data Index: 874061 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0777. Min Act: -0.0001

Data Index: 790443 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0824. Min Act: -0.0001

Data Index: 785434 (C4 (Web Text))

Max Activating Token Index: 920