Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3645 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1512372 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1632786 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1596631 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1606813 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1368359 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1628226 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1398435 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1580468 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1370444 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1491403 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1580016 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1580513 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1425913 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1615198 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1543277 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1424920 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1618137 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1446915 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1524385 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1382809 (Python Code)

Max Activating Token Index: 7