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

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

Neuron 5425 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: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1587847 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1487251 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1605926 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1569303 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1408891 (Python Code)

Max Activating Token Index: 798

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1452919 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1434985 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1440231 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1474800 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1423234 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1656588 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1512381 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1606640 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1570714 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1564495 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1375098 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1504282 (Python Code)

Max Activating Token Index: 516

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1574215 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1582107 (Python Code)

Max Activating Token Index: 645

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1443862 (Python Code)

Max Activating Token Index: 1003