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

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

Neuron 4437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1647792 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1597854 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1648522 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1499054 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1382260 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1382222 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1423840 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1446667 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1487908 (Python Code)

Max Activating Token Index: 855

Text #9

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1497570 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1409891 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1553470 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1655168 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1371785 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1643001 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1549112 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1516444 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1432955 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1569245 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1599904 (Python Code)

Max Activating Token Index: 757