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

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

Neuron 4391 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.2900. Min Act: -0.0001

Data Index: 1535583 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.6684. Min Act: -0.0001

Data Index: 1609614 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.6967. Min Act: -0.0001

Data Index: 1538007 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.7929. Min Act: -0.0001

Data Index: 1531770 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.0548. Min Act: -0.0001

Data Index: 1584632 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.9017. Min Act: -0.0001

Data Index: 1574786 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.6185. Min Act: -0.0001

Data Index: 1451475 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.4415. Min Act: -0.0001

Data Index: 1377327 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.3516. Min Act: -0.0001

Data Index: 1565851 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2686. Min Act: -0.0001

Data Index: 1381111 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2829. Min Act: -0.0001

Data Index: 1524782 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.3564. Min Act: -0.0001

Data Index: 1593478 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2907. Min Act: -0.0001

Data Index: 1553002 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1521417 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2018. Min Act: -0.0001

Data Index: 1385086 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2806. Min Act: -0.0001

Data Index: 1478842 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.2006. Min Act: -0.0001

Data Index: 1456617 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.1152. Min Act: -0.0001

Data Index: 1382140 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1509260 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.0880. Min Act: -0.0001

Data Index: 1436389 (Python Code)

Max Activating Token Index: 577