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

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

Neuron 1878 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: 1.1278. Min Range: -1.1278

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1552353 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1568589 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1559175 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1499126 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1393029 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1550824 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1627510 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1580967 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1479710 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1629372 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1394868 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1644159 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1386263 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1533879 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1638321 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1413707 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 1.1278. Min Range: -1.1278

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1487209 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1429084 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1472473 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 1.1278. Min Range: -1.1278

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1541212 (Python Code)

Max Activating Token Index: 557