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

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

Neuron 4421 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.2720. Min Act: -0.0000

Data Index: 1392469 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.1882. Min Act: -0.0000

Data Index: 1454310 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.2278. Min Act: -0.0000

Data Index: 1401586 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.6630. Min Act: -0.0000

Data Index: 1461158 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.7374. Min Act: -0.0000

Data Index: 1423948 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.4984. Min Act: -0.0000

Data Index: 1540587 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.5963. Min Act: -0.0000

Data Index: 1397797 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.3402. Min Act: -0.0000

Data Index: 1368891 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.6921. Min Act: -0.0000

Data Index: 1619939 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.0873. Min Act: -0.0000

Data Index: 1401796 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.4357. Min Act: -0.0000

Data Index: 1534213 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.3719. Min Act: -0.0000

Data Index: 1364249 (Python Code)

Max Activating Token Index: 962

Text #12

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.0124. Min Act: -0.0000

Data Index: 1425983 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.5519. Min Act: -0.0000

Data Index: 1655902 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.3260. Min Act: -0.0000

Data Index: 1595727 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.3845. Min Act: -0.0000

Data Index: 1615270 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.2049. Min Act: -0.0000

Data Index: 1644500 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.1802. Min Act: -0.0000

Data Index: 1431245 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.0027. Min Act: -0.0000

Data Index: 1385647 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.1392. Min Act: -0.0000

Data Index: 1453804 (Python Code)

Max Activating Token Index: 922