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

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

Neuron 4913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1499327 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.2942. Min Act: 0.0000

Data Index: 1570930 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.1391. Min Act: -0.0000

Data Index: 1430333 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.0444. Min Act: -0.0000

Data Index: 1506554 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.9138. Min Act: -0.0000

Data Index: 1621702 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1575201 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.0027. Min Act: -0.0000

Data Index: 1498289 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.9039. Min Act: 0.0000

Data Index: 1371037 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1516112 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.8219. Min Act: -0.0000

Data Index: 1412525 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.9741. Min Act: -0.0000

Data Index: 1459245 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7748. Min Act: 0.0000

Data Index: 1425178 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1449920 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7914. Min Act: 0.0000

Data Index: 1598731 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1569842 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1473084 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 2.4430. Min Range: -2.4430

Max Act: 2.0296. Min Act: -0.0000

Data Index: 1456526 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1390195 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1430824 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 2.4430. Min Range: -2.4430

Max Act: 1.6950. Min Act: 0.0000

Data Index: 1619898 (Python Code)

Max Activating Token Index: 911