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

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

Neuron 3883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.9572. Min Act: -0.0000

Data Index: 1449157 (Python Code)

Max Activating Token Index: 288

Text #1

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.3284. Min Act: -0.0000

Data Index: 1498954 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.2929. Min Act: -0.0000

Data Index: 1651943 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1419327 (Python Code)

Max Activating Token Index: 739

Text #4

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1570443 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.1516. Min Act: -0.0000

Data Index: 1420615 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.8813. Min Act: -0.0000

Data Index: 1603456 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 2.9572. Min Range: -2.9572

Max Act: 2.0154. Min Act: -0.0000

Data Index: 1629399 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.9714. Min Act: -0.0000

Data Index: 1592345 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.8425. Min Act: -0.0000

Data Index: 1572562 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.8748. Min Act: -0.0000

Data Index: 1525868 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.9730. Min Act: -0.0000

Data Index: 1499002 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7409. Min Act: -0.0000

Data Index: 1592173 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1392486 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7887. Min Act: -0.0000

Data Index: 1478449 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1580137 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.8400. Min Act: -0.0000

Data Index: 1380345 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7346. Min Act: -0.0000

Data Index: 1648033 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1456258 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 2.9572. Min Range: -2.9572

Max Act: 1.7194. Min Act: -0.0000

Data Index: 1530815 (Python Code)

Max Activating Token Index: 42