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

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

Neuron 5984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.4038. Min Act: -0.0000

Data Index: 432201 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3281. Min Act: -0.0000

Data Index: 995190 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3078. Min Act: -0.0000

Data Index: 229920 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2706. Min Act: -0.0000

Data Index: 543913 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2907. Min Act: -0.0000

Data Index: 714836 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2424. Min Act: -0.0000

Data Index: 489680 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2656. Min Act: -0.0000

Data Index: 651824 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1161892 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2773. Min Act: -0.0000

Data Index: 100879 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2718. Min Act: -0.0000

Data Index: 977690 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2529. Min Act: -0.0000

Data Index: 604965 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2695. Min Act: -0.0000

Data Index: 395841 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2789. Min Act: -0.0000

Data Index: 747543 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1180548 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2607. Min Act: -0.0000

Data Index: 168060 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2565. Min Act: -0.0000

Data Index: 976626 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2840. Min Act: -0.0000

Data Index: 784031 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1137291 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2729. Min Act: -0.0000

Data Index: 266761 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1229733 (C4 (Web Text))

Max Activating Token Index: 48