Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.7600. Min Act: -0.0000

Data Index: 1625346 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.6563. Min Act: -0.0000

Data Index: 1436646 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.6124. Min Act: -0.0000

Data Index: 1419797 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.4723. Min Act: -0.0000

Data Index: 1367535 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.4765. Min Act: -0.0000

Data Index: 1417977 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.9486. Min Act: -0.0000

Data Index: 1392463 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.7926. Min Act: -0.0000

Data Index: 1395773 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.8007. Min Act: -0.0000

Data Index: 1651985 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.7850. Min Act: -0.0000

Data Index: 1458115 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.8161. Min Act: -0.0000

Data Index: 1596459 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 5.7600. Min Range: -5.7600

Max Act: 5.0057. Min Act: -0.0000

Data Index: 1507235 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.5832. Min Act: -0.0000

Data Index: 1479964 (Python Code)

Max Activating Token Index: 253

Text #12

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.7718. Min Act: -0.0000

Data Index: 1404043 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.3369. Min Act: -0.0000

Data Index: 1626495 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.5475. Min Act: -0.0000

Data Index: 1361755 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.6665. Min Act: -0.0000

Data Index: 1595837 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.2288. Min Act: -0.0000

Data Index: 1377785 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.4171. Min Act: -0.0000

Data Index: 1626268 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.3529. Min Act: -0.0000

Data Index: 1424859 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 5.7600. Min Range: -5.7600

Max Act: 4.3591. Min Act: -0.0000

Data Index: 1458446 (Python Code)

Max Activating Token Index: 17