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

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

Neuron 428 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: 2.5084. Min Range: -2.5084

Max Act: 2.5084. Min Act: -0.0001

Data Index: 1431988 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1117. Min Act: -0.0001

Data Index: 1587547 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.2295. Min Act: -0.0000

Data Index: 1607777 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0934. Min Act: -0.0000

Data Index: 1477907 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1885. Min Act: -0.0000

Data Index: 1454998 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.2831. Min Act: -0.0001

Data Index: 1391737 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1575. Min Act: -0.0001

Data Index: 1505558 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0133. Min Act: -0.0001

Data Index: 1427513 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0074. Min Act: -0.0000

Data Index: 1474414 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1165. Min Act: -0.0001

Data Index: 1611162 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1971. Min Act: -0.0001

Data Index: 1439720 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1420926 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0786. Min Act: -0.0001

Data Index: 1469394 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0526. Min Act: -0.0001

Data Index: 1567148 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 2.5084. Min Range: -2.5084

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1521056 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 2.5084. Min Range: -2.5084

Max Act: 1.9370. Min Act: -0.0000

Data Index: 1561991 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1610543 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 2.5084. Min Range: -2.5084

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1551970 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 2.5084. Min Range: -2.5084

Max Act: 1.8977. Min Act: -0.0001

Data Index: 1426587 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 2.5084. Min Range: -2.5084

Max Act: 1.8007. Min Act: -0.0001

Data Index: 1434130 (Python Code)

Max Activating Token Index: 34