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

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

Neuron 1114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6990. Min Act: -0.0000

Data Index: 1561933 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1522526 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1642203 (Python Code)

Max Activating Token Index: 703

Text #3

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1381833 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1530581 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9447. Min Act: -0.0001

Data Index: 1428076 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1611694 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1462588 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1432543 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1373046 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1495373 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9362. Min Act: -0.0000

Data Index: 981490 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8813. Min Act: -0.0001

Data Index: 1525337 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1635969 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1600512 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1586279 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1554541 (Python Code)

Max Activating Token Index: 748

Text #17

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1563424 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1561744 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1537389 (Python Code)

Max Activating Token Index: 618