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

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

Neuron 5677 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: 1.1654. Min Range: -1.1654

Max Act: 1.1605. Min Act: -0.0002

Data Index: 97677 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1654. Min Act: -0.0002

Data Index: 483560 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1578. Min Act: -0.0002

Data Index: 263620 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1258. Min Act: -0.0002

Data Index: 216819 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1004. Min Act: -0.0003

Data Index: 144627 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0835. Min Act: -0.0002

Data Index: 1324612 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0738. Min Act: -0.0002

Data Index: 226988 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0314. Min Act: -0.0002

Data Index: 225483 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0235. Min Act: -0.0002

Data Index: 1328606 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0422. Min Act: -0.0002

Data Index: 1153148 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0333. Min Act: -0.0002

Data Index: 1254797 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0097. Min Act: -0.0003

Data Index: 171077 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0002. Min Act: -0.0002

Data Index: 55286 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0283. Min Act: -0.0002

Data Index: 80587 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9905. Min Act: -0.0002

Data Index: 753818 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0013. Min Act: -0.0002

Data Index: 433750 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9919. Min Act: -0.0003

Data Index: 214213 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9938. Min Act: -0.0002

Data Index: 1002596 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9992. Min Act: -0.0003

Data Index: 11705 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9955. Min Act: -0.0002

Data Index: 817027 (C4 (Web Text))

Max Activating Token Index: 89