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

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

Neuron 503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.8000. Min Act: -0.0001

Data Index: 1441775 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.7552. Min Act: -0.0001

Data Index: 1451173 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.6564. Min Act: -0.0001

Data Index: 1430948 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.7339. Min Act: -0.0001

Data Index: 1520416 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.6053. Min Act: -0.0001

Data Index: 1622709 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.6340. Min Act: -0.0001

Data Index: 1579114 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.6253. Min Act: -0.0001

Data Index: 1456698 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5494. Min Act: -0.0001

Data Index: 1481826 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.6083. Min Act: -0.0001

Data Index: 1421874 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5550. Min Act: -0.0001

Data Index: 1552243 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5480. Min Act: -0.0001

Data Index: 1557961 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.4682. Min Act: -0.0001

Data Index: 1597424 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5463. Min Act: -0.0001

Data Index: 1374506 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5002. Min Act: -0.0001

Data Index: 1650847 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5482. Min Act: -0.0001

Data Index: 1526711 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.4488. Min Act: -0.0001

Data Index: 1649300 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5278. Min Act: -0.0001

Data Index: 1544624 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.5488. Min Act: -0.0001

Data Index: 1373843 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.4587. Min Act: -0.0001

Data Index: 1482941 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 1.8000. Min Range: -1.8000

Max Act: 1.4494. Min Act: -0.0001

Data Index: 1452197 (Python Code)

Max Activating Token Index: 13