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

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

Neuron 2714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9331. Min Act: -0.0001

Data Index: 1294626 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9051. Min Act: -0.0001

Data Index: 1165008 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1313034 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8850. Min Act: -0.0001

Data Index: 311144 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8570. Min Act: -0.0002

Data Index: 260032 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8749. Min Act: -0.0002

Data Index: 1187430 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8695. Min Act: -0.0001

Data Index: 744805 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8629. Min Act: -0.0001

Data Index: 1326019 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8928. Min Act: -0.0001

Data Index: 20346 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9134. Min Act: -0.0002

Data Index: 824104 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8350. Min Act: -0.0001

Data Index: 56246 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8677. Min Act: -0.0001

Data Index: 119344 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1327017 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8737. Min Act: -0.0002

Data Index: 362593 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8340. Min Act: -0.0001

Data Index: 953464 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8564. Min Act: -0.0001

Data Index: 201113 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1049957 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8286. Min Act: -0.0002

Data Index: 790434 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8414. Min Act: -0.0002

Data Index: 895435 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.8130. Min Act: -0.0002

Data Index: 232477 (C4 (Web Text))

Max Activating Token Index: 426