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

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

Neuron 3067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1206321 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0708. Min Act: -0.0000

Data Index: 32823 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0735. Min Act: -0.0000

Data Index: 448142 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0000

Data Index: 239990 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0605. Min Act: -0.0001

Data Index: 923302 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0625. Min Act: -0.0000

Data Index: 51646 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0706. Min Act: -0.0000

Data Index: 289017 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0708. Min Act: -0.0001

Data Index: 343205 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0659. Min Act: -0.0000

Data Index: 87744 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0725. Min Act: -0.0001

Data Index: 107251 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1946 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0724. Min Act: -0.0001

Data Index: 263878 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0692. Min Act: -0.0000

Data Index: 406715 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0561. Min Act: -0.0000

Data Index: 168405 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0667. Min Act: -0.0001

Data Index: 263637 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1345072 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0675. Min Act: -0.0000

Data Index: 564904 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0000

Data Index: 987948 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0641. Min Act: -0.0001

Data Index: 978292 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0631. Min Act: -0.0000

Data Index: 112321 (C4 (Web Text))

Max Activating Token Index: 874