Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1985 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0003

Data Index: 386119 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0737. Min Act: -0.0003

Data Index: 713758 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1023898 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0710. Min Act: -0.0003

Data Index: 515149 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0717. Min Act: -0.0002

Data Index: 707948 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0691. Min Act: -0.0003

Data Index: 367302 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0680. Min Act: -0.0004

Data Index: 329739 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0666. Min Act: -0.0003

Data Index: 184607 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0676. Min Act: -0.0003

Data Index: 780576 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0683. Min Act: -0.0003

Data Index: 737166 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1188872 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0653. Min Act: -0.0003

Data Index: 201313 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1245736 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0666. Min Act: -0.0003

Data Index: 279221 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0622. Min Act: -0.0003

Data Index: 213570 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0689. Min Act: -0.0003

Data Index: 704285 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1098982 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0631. Min Act: -0.0003

Data Index: 142821 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0649. Min Act: -0.0003

Data Index: 629235 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0637. Min Act: -0.0003

Data Index: 458265 (C4 (Web Text))

Max Activating Token Index: 989