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

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

Neuron 3667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9895. Min Act: -0.0002

Data Index: 1381159 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9896. Min Act: -0.0002

Data Index: 1458692 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9504. Min Act: -0.0002

Data Index: 1561687 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9546. Min Act: -0.0002

Data Index: 1621758 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9392. Min Act: -0.0002

Data Index: 1615490 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9575. Min Act: -0.0002

Data Index: 1592623 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9325. Min Act: -0.0002

Data Index: 1645138 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9291. Min Act: -0.0002

Data Index: 1511943 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9220. Min Act: -0.0002

Data Index: 1480988 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9131. Min Act: -0.0002

Data Index: 1443726 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8926. Min Act: -0.0002

Data Index: 1615627 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8765. Min Act: -0.0002

Data Index: 1378981 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8891. Min Act: -0.0002

Data Index: 1482847 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9051. Min Act: -0.0002

Data Index: 1451498 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8837. Min Act: -0.0002

Data Index: 1386563 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9017. Min Act: -0.0002

Data Index: 1434927 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8968. Min Act: -0.0002

Data Index: 1635323 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8898. Min Act: -0.0002

Data Index: 1580311 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8707. Min Act: -0.0002

Data Index: 1605750 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8775. Min Act: -0.0002

Data Index: 1395524 (Python Code)

Max Activating Token Index: 422