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

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

Neuron 259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4692. Min Act: -0.0002

Data Index: 1650583 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4344. Min Act: -0.0002

Data Index: 1566735 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4175. Min Act: -0.0002

Data Index: 1524171 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4124. Min Act: -0.0002

Data Index: 1454368 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4247. Min Act: -0.0002

Data Index: 1536522 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4235. Min Act: -0.0002

Data Index: 1375201 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4188. Min Act: -0.0002

Data Index: 1640071 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4098. Min Act: -0.0002

Data Index: 1596434 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3929. Min Act: -0.0002

Data Index: 1452830 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4067. Min Act: -0.0002

Data Index: 1470341 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4085. Min Act: -0.0002

Data Index: 1471972 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4052. Min Act: -0.0002

Data Index: 1475690 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3943. Min Act: -0.0002

Data Index: 1439286 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3961. Min Act: -0.0002

Data Index: 1528775 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3814. Min Act: -0.0002

Data Index: 1588673 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3772. Min Act: -0.0002

Data Index: 1386194 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3785. Min Act: -0.0002

Data Index: 1449694 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3919. Min Act: -0.0002

Data Index: 1579173 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3884. Min Act: -0.0002

Data Index: 1513107 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3643. Min Act: -0.0002

Data Index: 1587851 (Python Code)

Max Activating Token Index: 7