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

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

Neuron 753 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: 0.8783. Min Range: -0.8783

Max Act: 0.8783. Min Act: -0.0002

Data Index: 1475678 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7870. Min Act: -0.0002

Data Index: 1409922 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7627. Min Act: -0.0002

Data Index: 1567205 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7509. Min Act: -0.0002

Data Index: 1518281 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7288. Min Act: -0.0002

Data Index: 1411532 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6993. Min Act: -0.0002

Data Index: 1420764 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6884. Min Act: -0.0002

Data Index: 1597960 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6850. Min Act: -0.0002

Data Index: 1435515 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6821. Min Act: -0.0002

Data Index: 1533973 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6691. Min Act: -0.0002

Data Index: 1513776 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6673. Min Act: -0.0002

Data Index: 1635067 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6475. Min Act: -0.0002

Data Index: 1453997 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6380. Min Act: -0.0002

Data Index: 1536393 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6358. Min Act: -0.0002

Data Index: 1655416 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6296. Min Act: -0.0002

Data Index: 1493516 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6298. Min Act: -0.0002

Data Index: 1545502 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6267. Min Act: -0.0002

Data Index: 1596678 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6123. Min Act: -0.0002

Data Index: 1380453 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6020. Min Act: -0.0002

Data Index: 1470555 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6042. Min Act: -0.0002

Data Index: 1562057 (Python Code)

Max Activating Token Index: 12