Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9723. Min Act: -0.0001

Data Index: 1011830 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8742. Min Act: -0.0000

Data Index: 774620 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8559. Min Act: -0.0001

Data Index: 491991 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8397. Min Act: -0.0001

Data Index: 1036044 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8344. Min Act: -0.0001

Data Index: 941804 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7634. Min Act: -0.0001

Data Index: 251502 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7463. Min Act: -0.0001

Data Index: 936428 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7753. Min Act: -0.0001

Data Index: 22174 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7680. Min Act: -0.0001

Data Index: 1322467 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7817. Min Act: -0.0001

Data Index: 714953 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7964. Min Act: -0.0001

Data Index: 460465 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7381. Min Act: -0.0001

Data Index: 801444 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7445. Min Act: -0.0001

Data Index: 753653 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6844. Min Act: -0.0001

Data Index: 1312379 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.7164. Min Act: -0.0001

Data Index: 843233 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6699. Min Act: -0.0001

Data Index: 1106099 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6603. Min Act: -0.0001

Data Index: 873136 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6895. Min Act: -0.0001

Data Index: 1300788 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6896. Min Act: -0.0001

Data Index: 276340 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.6912. Min Act: -0.0001

Data Index: 1136255 (C4 (Web Text))

Max Activating Token Index: 83