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

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

Neuron 1080 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2824. Min Act: -0.0001

Data Index: 492188 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2738. Min Act: -0.0001

Data Index: 380028 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2721. Min Act: -0.0001

Data Index: 459074 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2611. Min Act: -0.0001

Data Index: 621807 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2696. Min Act: -0.0001

Data Index: 486909 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2540. Min Act: -0.0001

Data Index: 463440 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2652. Min Act: -0.0001

Data Index: 537134 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2813. Min Act: -0.0001

Data Index: 690976 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2611. Min Act: -0.0001

Data Index: 492838 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1328196 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1153576 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1283789 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2601. Min Act: -0.0001

Data Index: 116050 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1312769 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1033850 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2377. Min Act: -0.0001

Data Index: 772151 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2581. Min Act: -0.0001

Data Index: 531066 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2536. Min Act: -0.0001

Data Index: 433533 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1223523 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2519. Min Act: -0.0001

Data Index: 72598 (C4 (Web Text))

Max Activating Token Index: 133