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

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

Neuron 1487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.4894. Min Act: -0.0001

Data Index: 1614308 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.2330. Min Act: -0.0001

Data Index: 1469742 (Python Code)

Max Activating Token Index: 729

Text #2

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.4981. Min Act: -0.0001

Data Index: 957563 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.6641. Min Act: -0.0001

Data Index: 1365555 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.0893. Min Act: -0.0001

Data Index: 1526820 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.2614. Min Act: -0.0001

Data Index: 1531309 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.1019. Min Act: -0.0001

Data Index: 1501537 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.1188. Min Act: -0.0001

Data Index: 1621420 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.0506. Min Act: -0.0001

Data Index: 1652458 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.0962. Min Act: -0.0001

Data Index: 1567798 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.2799. Min Act: -0.0001

Data Index: 1404237 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 3.6641. Min Range: -3.6641

Max Act: 2.9797. Min Act: -0.0001

Data Index: 1513067 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.2379. Min Act: -0.0001

Data Index: 1467281 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.1030. Min Act: -0.0001

Data Index: 1585614 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.0928. Min Act: -0.0001

Data Index: 1626621 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 3.6641. Min Range: -3.6641

Max Act: 2.9631. Min Act: -0.0001

Data Index: 1391073 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 3.6641. Min Range: -3.6641

Max Act: 2.9645. Min Act: -0.0001

Data Index: 1590487 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.2238. Min Act: -0.0001

Data Index: 1438092 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 3.6641. Min Range: -3.6641

Max Act: 2.9705. Min Act: -0.0001

Data Index: 1565611 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 3.6641. Min Range: -3.6641

Max Act: 3.0678. Min Act: -0.0001

Data Index: 1436031 (Python Code)

Max Activating Token Index: 830