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

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

Neuron 2586 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0906. Min Range: -1.0906

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1431651 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 1.0906. Min Range: -1.0906

Max Act: 1.0675. Min Act: 0.0000

Data Index: 1528319 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1588362 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8974. Min Act: 0.0000

Data Index: 1398544 (Python Code)

Max Activating Token Index: 1017

Text #4

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1478503 (Python Code)

Max Activating Token Index: 715

Text #5

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1504701 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1614845 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1608862 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1522759 (Python Code)

Max Activating Token Index: 650

Text #9

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1529359 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1633307 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1638165 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8010. Min Act: 0.0000

Data Index: 1378303 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1538153 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1447646 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1600633 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1487033 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1603963 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1418023 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1498672 (Python Code)

Max Activating Token Index: 556