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

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

Neuron 2028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9842. Min Act: -0.0000

Data Index: 343891 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9907. Min Act: -0.0000

Data Index: 983785 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9660. Min Act: -0.0000

Data Index: 977943 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8621. Min Act: -0.0000

Data Index: 754509 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1101528 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1339820 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1111655 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8482. Min Act: -0.0000

Data Index: 67829 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8417. Min Act: -0.0000

Data Index: 878860 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1021861 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8373. Min Act: -0.0000

Data Index: 239981 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8014. Min Act: -0.0000

Data Index: 320450 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1285101 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8268. Min Act: -0.0000

Data Index: 596061 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1122263 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7582. Min Act: -0.0000

Data Index: 91827 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7686. Min Act: -0.0000

Data Index: 324735 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7711. Min Act: -0.0000

Data Index: 727006 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7594. Min Act: -0.0000

Data Index: 703476 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1014844 (C4 (Web Text))

Max Activating Token Index: 820