Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7133. Min Act: -0.0001

Data Index: 1623022 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7219. Min Act: -0.0001

Data Index: 1559830 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.5419. Min Act: -0.0001

Data Index: 1647017 (Python Code)

Max Activating Token Index: 856

Text #3

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1497009 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1525317 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6479. Min Act: -0.0001

Data Index: 1453992 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1496285 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7356. Min Act: -0.0001

Data Index: 1618913 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1492242 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1456413 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1371796 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1403123 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1618322 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6779. Min Act: -0.0001

Data Index: 1552023 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1388921 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1559487 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1534007 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1458782 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6681. Min Act: -0.0001

Data Index: 1592418 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 0.7356. Min Range: -0.7356

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1535830 (Python Code)

Max Activating Token Index: 42