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

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

Neuron 3044 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1399628 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1362433 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1360910 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1419770 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1520648 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1539240 (Python Code)

Max Activating Token Index: 885

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1652278 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1458750 (Python Code)

Max Activating Token Index: 592

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1618203 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1377454 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1506960 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1416833 (Python Code)

Max Activating Token Index: 792

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1409998 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1471689 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1512439 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1655744 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1396697 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1650348 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1401961 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 592