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

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

Neuron 629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1510801 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1475215 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1492265 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1639653 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1522405 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1635875 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1498050 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1571552 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1411910 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1562527 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1374682 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8370. Min Act: -0.0000

Data Index: 855056 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1457767 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1384803 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1458448 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1612706 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1546506 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1451385 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1525433 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1561396 (Python Code)

Max Activating Token Index: 708