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

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

Neuron 782 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: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1371336 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1589266 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1622976 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1632536 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1553946 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1382792 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1394194 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1449125 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1588209 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1652413 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1641015 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1492155 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1447796 (Python Code)

Max Activating Token Index: 756

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1592252 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1516702 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1563721 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1474930 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1483050 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1478249 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1481725 (Python Code)

Max Activating Token Index: 407