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

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

Neuron 4446 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.5733. Min Act: -0.0001

Data Index: 1591093 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.1696. Min Act: -0.0001

Data Index: 1387949 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.2874. Min Act: -0.0001

Data Index: 1534256 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.2139. Min Act: -0.0001

Data Index: 1649654 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.2120. Min Act: -0.0001

Data Index: 1443739 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.1950. Min Act: -0.0001

Data Index: 1567976 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.3702. Min Act: -0.0001

Data Index: 1544333 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.1477. Min Act: -0.0001

Data Index: 1423054 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.3124. Min Act: -0.0001

Data Index: 1468826 (Python Code)

Max Activating Token Index: 839

Text #9

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.2884. Min Act: -0.0001

Data Index: 1418117 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8797. Min Act: -0.0001

Data Index: 1478777 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8709. Min Act: -0.0001

Data Index: 1447985 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.7041. Min Act: -0.0001

Data Index: 1410582 (Python Code)

Max Activating Token Index: 894

Text #13

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8719. Min Act: -0.0001

Data Index: 1400457 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8586. Min Act: -0.0001

Data Index: 1604650 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.0227. Min Act: -0.0001

Data Index: 1568126 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.2099. Min Act: -0.0001

Data Index: 1434803 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8499. Min Act: -0.0001

Data Index: 1420528 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 5.5733. Min Range: -5.5733

Max Act: 4.8273. Min Act: -0.0001

Data Index: 1370012 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 5.5733. Min Range: -5.5733

Max Act: 5.0324. Min Act: -0.0001

Data Index: 1461185 (Python Code)

Max Activating Token Index: 786