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

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

Neuron 503 in Layer 0

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: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0001

Data Index: 380148 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1489996 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1641741 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1419112 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1437737 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1625205 (Python Code)

Max Activating Token Index: 371

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1551900 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1523108 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1606105 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1584162 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1444648 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1604095 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0799. Min Act: -0.0001

Data Index: 510493 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1403573 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1641565 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1458688 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1587803 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1598117 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1556221 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1562273 (Python Code)

Max Activating Token Index: 41