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

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

Neuron 5099 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: 0.8827. Min Range: -0.8827

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1381736 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1368808 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1585504 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7734. Min Act: -0.0001

Data Index: 1518236 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1616694 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1504686 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1430534 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1539133 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1410323 (Python Code)

Max Activating Token Index: 751

Text #9

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1445141 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1469658 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1390655 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1595663 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1483825 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1603594 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1388173 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1548735 (Python Code)

Max Activating Token Index: 703

Text #17

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1420043 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1592424 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1621671 (Python Code)

Max Activating Token Index: 356