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

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

Neuron 484 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.9362. Min Act: -0.0001

Data Index: 1613464 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.9100. Min Act: -0.0001

Data Index: 1361304 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.9517. Min Act: -0.0001

Data Index: 1529919 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.8218. Min Act: -0.0001

Data Index: 1511955 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.8081. Min Act: -0.0001

Data Index: 1461899 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.7608. Min Act: -0.0001

Data Index: 1627746 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.8066. Min Act: -0.0001

Data Index: 1426938 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.7581. Min Act: -0.0001

Data Index: 1572350 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.7222. Min Act: -0.0001

Data Index: 1369478 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.7503. Min Act: -0.0001

Data Index: 1510659 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.6356. Min Act: -0.0001

Data Index: 1450991 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.6712. Min Act: -0.0001

Data Index: 1648643 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.6192. Min Act: -0.0001

Data Index: 1524496 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5601. Min Act: -0.0001

Data Index: 1477313 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5563. Min Act: -0.0001

Data Index: 1379808 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5692. Min Act: -0.0001

Data Index: 1505397 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5198. Min Act: -0.0001

Data Index: 1475076 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5187. Min Act: -0.0001

Data Index: 1382295 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.6024. Min Act: -0.0001

Data Index: 1565589 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5060. Min Act: -0.0001

Data Index: 1556734 (Python Code)

Max Activating Token Index: 10