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

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

Neuron 1180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0612. Min Act: -0.0001

Data Index: 818049 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1479654 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1069055 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0663. Min Act: -0.0001

Data Index: 223618 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0648. Min Act: -0.0001

Data Index: 104818 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1427885 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0578. Min Act: -0.0001

Data Index: 848213 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0567. Min Act: -0.0001

Data Index: 445197 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1537916 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0621. Min Act: -0.0001

Data Index: 215604 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0591. Min Act: -0.0001

Data Index: 377680 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1536155 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1201721 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1596898 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0578. Min Act: -0.0001

Data Index: 156791 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1555730 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1116805 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0499. Min Act: -0.0001

Data Index: 555443 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1522389 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1269860 (C4 (Web Text))

Max Activating Token Index: 17