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

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

Neuron 4321 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.6596. Min Act: -0.0000

Data Index: 1435976 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1571067 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1564169 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1558694 (Python Code)

Max Activating Token Index: 379

Text #4

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1613158 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1648293 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8971. Min Act: 0.0000

Data Index: 1382601 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1430861 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1375591 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1550811 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1574673 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1430553 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1470635 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1409633 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1447454 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1591610 (Python Code)

Max Activating Token Index: 715

Text #16

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1541682 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1570472 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1555102 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1475799 (Python Code)

Max Activating Token Index: 345