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

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

Neuron 217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.8450. Min Act: -0.0000

Data Index: 1425757 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.7526. Min Act: -0.0000

Data Index: 1651348 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.7193. Min Act: -0.0000

Data Index: 1453855 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.6005. Min Act: -0.0000

Data Index: 1531844 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.1300. Min Act: -0.0000

Data Index: 1599803 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1545394 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1459447 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.1683. Min Act: -0.0000

Data Index: 1653293 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.2179. Min Act: -0.0000

Data Index: 1503440 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.0826. Min Act: -0.0000

Data Index: 1371156 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.0030. Min Act: -0.0001

Data Index: 1449882 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.0215. Min Act: -0.0000

Data Index: 1441772 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 2.8450. Min Range: -2.8450

Max Act: 2.0538. Min Act: -0.0000

Data Index: 1459617 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.9869. Min Act: -0.0000

Data Index: 1506435 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1470748 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.9249. Min Act: -0.0000

Data Index: 1505483 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.8880. Min Act: -0.0001

Data Index: 1516102 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1509944 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.8687. Min Act: -0.0000

Data Index: 1426759 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 2.8450. Min Range: -2.8450

Max Act: 1.9444. Min Act: -0.0000

Data Index: 1385086 (Python Code)

Max Activating Token Index: 170