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

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

Neuron 3002 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: 0.4852. Min Range: -0.4852

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1535528 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1622112 (Python Code)

Max Activating Token Index: 856

Text #2

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1553342 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1432816 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1478816 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1653483 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1520715 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1550927 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1408714 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1444563 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1612472 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1572039 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1468459 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1600992 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1625313 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1592709 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1637495 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1591693 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1618136 (Python Code)

Max Activating Token Index: 907

Text #19

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1525370 (Python Code)

Max Activating Token Index: 561