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

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

Neuron 2248 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: 0.9324. Min Range: -0.9324

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1552747 (Python Code)

Max Activating Token Index: 661

Text #1

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.9324. Min Act: -0.0001

Data Index: 1564700 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1528979 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8372. Min Act: -0.0001

Data Index: 1460874 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7920. Min Act: -0.0001

Data Index: 1494556 (Python Code)

Max Activating Token Index: 534

Text #5

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7973. Min Act: -0.0001

Data Index: 1451463 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1572241 (Python Code)

Max Activating Token Index: 613

Text #7

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8158. Min Act: -0.0001

Data Index: 1617724 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1589675 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8150. Min Act: -0.0001

Data Index: 1473335 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7854. Min Act: -0.0001

Data Index: 1633601 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8000. Min Act: -0.0001

Data Index: 1645887 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1451894 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1578462 (Python Code)

Max Activating Token Index: 569

Text #14

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7844. Min Act: -0.0001

Data Index: 1579797 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1543920 (Python Code)

Max Activating Token Index: 470

Text #16

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1514329 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7752. Min Act: -0.0001

Data Index: 1483594 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8044. Min Act: -0.0001

Data Index: 1644051 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1557453 (Python Code)

Max Activating Token Index: 545