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

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

Neuron 2393 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1583656 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1601022 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1434945 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1653407 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5112. Min Act: -0.0001

Data Index: 1604487 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1509840 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5309. Min Act: -0.0001

Data Index: 1524771 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1383531 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1483793 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1415101 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1589298 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1473618 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4963. Min Act: -0.0001

Data Index: 1497265 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1459000 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1586983 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4922. Min Act: -0.0001

Data Index: 1426325 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4872. Min Act: -0.0001

Data Index: 1532135 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4957. Min Act: -0.0001

Data Index: 1430351 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1556011 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4770. Min Act: -0.0001

Data Index: 1610099 (Python Code)

Max Activating Token Index: 18