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

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

Neuron 5812 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2049. Min Act: -0.0002

Data Index: 1379164 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2039. Min Act: -0.0002

Data Index: 1440170 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1983. Min Act: -0.0002

Data Index: 1404725 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1871. Min Act: -0.0002

Data Index: 1396614 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1896. Min Act: -0.0002

Data Index: 1604800 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1874. Min Act: -0.0002

Data Index: 1503263 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1933. Min Act: -0.0002

Data Index: 1647970 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1895. Min Act: -0.0002

Data Index: 1524687 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1875. Min Act: -0.0002

Data Index: 1519918 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1849. Min Act: -0.0002

Data Index: 1381193 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1830. Min Act: -0.0002

Data Index: 1618453 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1518064 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1628194 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1789. Min Act: -0.0002

Data Index: 1420805 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1808. Min Act: -0.0002

Data Index: 1647838 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1382862 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1643494 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1508166 (Python Code)

Max Activating Token Index: 134

Text #18

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1824. Min Act: -0.0002

Data Index: 1492245 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1792. Min Act: -0.0002

Data Index: 1370342 (Python Code)

Max Activating Token Index: 21