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

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

Neuron 2036 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: 12.0849. Min Range: -12.0849

Max Act: 12.0849. Min Act: -0.0000

Data Index: 1417707 (Python Code)

Max Activating Token Index: 736

Text #1

Max Range: 12.0849. Min Range: -12.0849

Max Act: 11.2610. Min Act: -0.0000

Data Index: 1570684 (Python Code)

Max Activating Token Index: 701

Text #2

Max Range: 12.0849. Min Range: -12.0849

Max Act: 10.9341. Min Act: -0.0000

Data Index: 1486671 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 12.0849. Min Range: -12.0849

Max Act: 10.3862. Min Act: -0.0000

Data Index: 1569929 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.3971. Min Act: -0.0000

Data Index: 1596593 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.3876. Min Act: -0.0000

Data Index: 1405553 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.3327. Min Act: -0.0000

Data Index: 1633062 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.1087. Min Act: -0.0000

Data Index: 1540642 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.5039. Min Act: -0.0000

Data Index: 1556931 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.3863. Min Act: -0.0000

Data Index: 1378333 (Python Code)

Max Activating Token Index: 184

Text #10

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.3458. Min Act: -0.0000

Data Index: 1517261 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.0703. Min Act: -0.0000

Data Index: 1500241 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.2328. Min Act: -0.0000

Data Index: 1549384 (Python Code)

Max Activating Token Index: 908

Text #13

Max Range: 12.0849. Min Range: -12.0849

Max Act: 9.0678. Min Act: -0.0000

Data Index: 1501109 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 12.0849. Min Range: -12.0849

Max Act: 8.9023. Min Act: -0.0000

Data Index: 1640870 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 12.0849. Min Range: -12.0849

Max Act: 8.3965. Min Act: -0.0000

Data Index: 1615649 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 12.0849. Min Range: -12.0849

Max Act: 8.3441. Min Act: -0.0000

Data Index: 1455686 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 12.0849. Min Range: -12.0849

Max Act: 8.2485. Min Act: -0.0000

Data Index: 1416841 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 12.0849. Min Range: -12.0849

Max Act: 8.5003. Min Act: -0.0000

Data Index: 1577594 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 12.0849. Min Range: -12.0849

Max Act: 7.9863. Min Act: -0.0000

Data Index: 1414949 (Python Code)

Max Activating Token Index: 490