Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 566 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.9638. Min Act: -0.0001

Data Index: 1583987 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1452315 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1479630 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1475076 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7979. Min Act: -0.0001

Data Index: 1525844 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1565589 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6696. Min Act: -0.0001

Data Index: 1412973 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6637. Min Act: -0.0001

Data Index: 1442825 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1636584 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1470687 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1477313 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1627746 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1531378 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1525768 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6495. Min Act: -0.0001

Data Index: 1560385 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1568683 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1507119 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1486057 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1512333 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6171. Min Act: -0.0001

Data Index: 1386889 (Python Code)

Max Activating Token Index: 17