Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1801 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1591199 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0735. Min Act: -0.0001

Data Index: 954987 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0658. Min Act: -0.0001

Data Index: 149106 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1401272 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0764. Min Act: -0.0000

Data Index: 914446 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1632428 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1520706 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1591169 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1443799 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1583234 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0638. Min Act: -0.0001

Data Index: 967781 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1010425 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1630926 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0602. Min Act: -0.0001

Data Index: 219120 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1443125 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1041671 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1504005 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1577738 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0659. Min Act: -0.0001

Data Index: 22628 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1019912 (C4 (Web Text))

Max Activating Token Index: 301