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

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

Neuron 2657 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9720. Min Range: -2.9720

Max Act: 2.9720. Min Act: -0.0000

Data Index: 1451308 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 2.9720. Min Range: -2.9720

Max Act: 2.3072. Min Act: -0.0000

Data Index: 1400829 (Python Code)

Max Activating Token Index: 589

Text #2

Max Range: 2.9720. Min Range: -2.9720

Max Act: 2.0567. Min Act: -0.0000

Data Index: 1409238 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.8092. Min Act: -0.0000

Data Index: 1485181 (Python Code)

Max Activating Token Index: 533

Text #4

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1385105 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1395761 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1511950 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 2.9720. Min Range: -2.9720

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1427284 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1450328 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1434209 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1391652 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1580140 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1482874 (Python Code)

Max Activating Token Index: 897

Text #13

Max Range: 2.9720. Min Range: -2.9720

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1440428 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1574789 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1617408 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1591623 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1434042 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 2.9720. Min Range: -2.9720

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1516293 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 2.9720. Min Range: -2.9720

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1423684 (Python Code)

Max Activating Token Index: 525