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

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

Neuron 1801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0001

Data Index: 1423983 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1615794 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4088. Min Act: -0.0001

Data Index: 1548702 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1425558 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4206. Min Act: -0.0001

Data Index: 1524824 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1551784 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4018. Min Act: -0.0001

Data Index: 1470987 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4097. Min Act: -0.0001

Data Index: 1466254 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1552295 (Python Code)

Max Activating Token Index: 183

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1482419 (Python Code)

Max Activating Token Index: 908

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1580433 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3959. Min Act: -0.0001

Data Index: 1541708 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3651. Min Act: -0.0001

Data Index: 1624098 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3797. Min Act: -0.0001

Data Index: 1507433 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3584. Min Act: -0.0001

Data Index: 1438558 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3576. Min Act: -0.0001

Data Index: 1408883 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1510514 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1555930 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3587. Min Act: -0.0001

Data Index: 1422356 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3580. Min Act: -0.0001

Data Index: 1641252 (Python Code)

Max Activating Token Index: 26