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

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

Neuron 2049 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.9039. Min Act: -0.0000

Data Index: 1444131 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1646947 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1618200 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1607316 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1513509 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1559210 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1589360 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1575413 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1515483 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1552603 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.6000. Min Act: -0.0000

Data Index: 1453545 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7633. Min Act: -0.0000

Data Index: 1578916 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1559780 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1558672 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1576487 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1527899 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1438480 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7231. Min Act: -0.0000

Data Index: 1604265 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.6311. Min Act: -0.0000

Data Index: 1403042 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.6858. Min Act: -0.0000

Data Index: 1426360 (Python Code)

Max Activating Token Index: 19