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

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

Neuron 344 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1632900 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1503877 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1413775 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1638970 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1386743 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1622733 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1510414 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1411862 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1575661 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1501073 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1380078 (Python Code)

Max Activating Token Index: 553

Text #11

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1427623 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1509460 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1450660 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1609236 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1365250 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1563210 (Python Code)

Max Activating Token Index: 458

Text #17

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1416525 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1410183 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1506997 (Python Code)

Max Activating Token Index: 176