Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 87 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0673. Min Act: -0.0005

Data Index: 302920 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0652. Min Act: -0.0005

Data Index: 941620 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0666. Min Act: -0.0005

Data Index: 73379 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0616. Min Act: -0.0005

Data Index: 189107 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0544. Min Act: -0.0005

Data Index: 1181024 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0623. Min Act: -0.0005

Data Index: 1092192 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0579. Min Act: -0.0005

Data Index: 171626 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0588. Min Act: -0.0005

Data Index: 194038 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0621. Min Act: -0.0005

Data Index: 180366 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0576. Min Act: -0.0005

Data Index: 804893 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0562. Min Act: -0.0005

Data Index: 750617 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0596. Min Act: -0.0005

Data Index: 289167 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0609. Min Act: -0.0005

Data Index: 1206624 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1305123 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0576. Min Act: -0.0005

Data Index: 1114907 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0619. Min Act: -0.0005

Data Index: 461799 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0580. Min Act: -0.0005

Data Index: 848786 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0515. Min Act: -0.0005

Data Index: 540309 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0555. Min Act: -0.0005

Data Index: 345150 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0565. Min Act: -0.0005

Data Index: 688935 (C4 (Web Text))

Max Activating Token Index: 563