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

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

Neuron 2686 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: 6.6105. Min Range: -6.6105

Max Act: 6.6105. Min Act: -0.0000

Data Index: 1406698 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 6.6105. Min Range: -6.6105

Max Act: 6.3462. Min Act: -0.0000

Data Index: 1376190 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 6.6105. Min Range: -6.6105

Max Act: 5.6374. Min Act: -0.0000

Data Index: 1395722 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 6.6105. Min Range: -6.6105

Max Act: 5.6131. Min Act: -0.0000

Data Index: 1436347 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 6.6105. Min Range: -6.6105

Max Act: 5.2294. Min Act: -0.0000

Data Index: 1593186 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 6.6105. Min Range: -6.6105

Max Act: 5.5753. Min Act: -0.0000

Data Index: 1409622 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 6.6105. Min Range: -6.6105

Max Act: 4.9250. Min Act: -0.0000

Data Index: 1627741 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 6.6105. Min Range: -6.6105

Max Act: 5.1859. Min Act: -0.0000

Data Index: 1374819 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 6.6105. Min Range: -6.6105

Max Act: 4.7711. Min Act: -0.0000

Data Index: 1615426 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 6.6105. Min Range: -6.6105

Max Act: 4.3303. Min Act: -0.0000

Data Index: 1560906 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 6.6105. Min Range: -6.6105

Max Act: 4.4767. Min Act: -0.0000

Data Index: 1429593 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 6.6105. Min Range: -6.6105

Max Act: 3.6717. Min Act: -0.0000

Data Index: 1551350 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 6.6105. Min Range: -6.6105

Max Act: 3.8094. Min Act: -0.0000

Data Index: 1453559 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.9413. Min Act: -0.0000

Data Index: 1153165 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.9360. Min Act: -0.0000

Data Index: 226305 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 6.6105. Min Range: -6.6105

Max Act: 3.0818. Min Act: -0.0000

Data Index: 1557661 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.6851. Min Act: -0.0000

Data Index: 1436375 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.8078. Min Act: -0.0000

Data Index: 1021455 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.7872. Min Act: -0.0000

Data Index: 373902 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 6.6105. Min Range: -6.6105

Max Act: 2.6097. Min Act: -0.0000

Data Index: 1481755 (Python Code)

Max Activating Token Index: 33