Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8593. Min Act: -0.0000

Data Index: 249559 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.9627. Min Act: -0.0000

Data Index: 401810 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 2.0133. Min Range: -2.0133

Max Act: 2.0133. Min Act: -0.0000

Data Index: 627279 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1630790 (Python Code)

Max Activating Token Index: 439

Text #4

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8756. Min Act: -0.0000

Data Index: 1576200 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8728. Min Act: -0.0000

Data Index: 1422502 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1405654 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8077. Min Act: -0.0000

Data Index: 1599694 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8985. Min Act: -0.0000

Data Index: 730346 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.8367. Min Act: -0.0000

Data Index: 512840 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.7405. Min Act: -0.0000

Data Index: 1463564 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1623704 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1650375 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1654559 (Python Code)

Max Activating Token Index: 361

Text #14

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1376692 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1563649 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1647483 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.3524. Min Act: -0.0000

Data Index: 18910 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1468790 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 2.0133. Min Range: -2.0133

Max Act: 1.6102. Min Act: -0.0000

Data Index: 1591728 (Python Code)

Max Activating Token Index: 437