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

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

Neuron 3192 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.4675. Min Act: -0.0000

Data Index: 19945 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1066959 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1022543 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.1640. Min Act: -0.0000

Data Index: 355225 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.0901. Min Act: -0.0000

Data Index: 862143 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.0085. Min Act: -0.0000

Data Index: 301986 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1313119 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1323498 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.0024. Min Act: -0.0000

Data Index: 47566 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8835. Min Act: -0.0000

Data Index: 687002 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.9284. Min Act: -0.0000

Data Index: 171313 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.9329. Min Act: -0.0000

Data Index: 922650 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1232300 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.9123. Min Act: -0.0000

Data Index: 330703 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.9098. Min Act: -0.0000

Data Index: 704413 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1023347 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8967. Min Act: -0.0000

Data Index: 610747 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8890. Min Act: -0.0000

Data Index: 329984 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.8520. Min Act: -0.0000

Data Index: 916867 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.4675. Min Range: -1.4675

Max Act: 0.7879. Min Act: -0.0000

Data Index: 733267 (C4 (Web Text))

Max Activating Token Index: 410