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

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

Neuron 1391 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1669. Min Range: -3.1669

Max Act: 3.1669. Min Act: -0.0000

Data Index: 1481863 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7298. Min Act: -0.0000

Data Index: 1597752 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 3.1669. Min Range: -3.1669

Max Act: 3.0254. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.9979. Min Act: -0.0000

Data Index: 1405818 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.6436. Min Act: -0.0000

Data Index: 1421103 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7384. Min Act: -0.0000

Data Index: 1437293 (Python Code)

Max Activating Token Index: 1002

Text #6

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7599. Min Act: -0.0000

Data Index: 1416425 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7599. Min Act: -0.0000

Data Index: 1489671 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7451. Min Act: -0.0000

Data Index: 1363522 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7451. Min Act: -0.0000

Data Index: 1535499 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7451. Min Act: -0.0000

Data Index: 1521779 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7137. Min Act: -0.0000

Data Index: 1381998 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.8027. Min Act: -0.0000

Data Index: 1556425 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.8027. Min Act: -0.0000

Data Index: 1364943 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1621865 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1613606 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.4850. Min Act: -0.0000

Data Index: 1444721 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.6274. Min Act: -0.0000

Data Index: 1551930 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.6083. Min Act: -0.0000

Data Index: 1651648 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 3.1669. Min Range: -3.1669

Max Act: 2.7362. Min Act: -0.0000

Data Index: 1564517 (Python Code)

Max Activating Token Index: 15