Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.3366. Min Act: -0.0001

Data Index: 1500782 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.4752. Min Act: -0.0000

Data Index: 1494204 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.3023. Min Act: -0.0000

Data Index: 1590377 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.2896. Min Act: -0.0000

Data Index: 1502029 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.2846. Min Act: -0.0000

Data Index: 1394418 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.2063. Min Act: -0.0000

Data Index: 1633121 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.2051. Min Act: -0.0001

Data Index: 1530483 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1735. Min Act: -0.0000

Data Index: 1449592 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1699. Min Act: -0.0000

Data Index: 1500068 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1662. Min Act: -0.0000

Data Index: 1569376 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1645. Min Act: -0.0000

Data Index: 1463427 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1680. Min Act: -0.0000

Data Index: 1628164 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1680. Min Act: -0.0000

Data Index: 1463054 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1680. Min Act: -0.0000

Data Index: 1574411 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.0019. Min Act: -0.0000

Data Index: 1548776 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1178. Min Act: -0.0000

Data Index: 1553163 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.1178. Min Act: -0.0000

Data Index: 1510479 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.0485. Min Act: -0.0000

Data Index: 1506589 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.4752. Min Range: -3.4752

Max Act: 3.0411. Min Act: -0.0001

Data Index: 1528167 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 3.4752. Min Range: -3.4752

Max Act: 2.8870. Min Act: -0.0001

Data Index: 1611860 (Python Code)

Max Activating Token Index: 24