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

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

Neuron 453 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0042. Min Range: -1.0042

Max Act: 1.0042. Min Act: -0.0000

Data Index: 563334 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8539. Min Act: -0.0000

Data Index: 430640 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1607954 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1606076 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8281. Min Act: -0.0000

Data Index: 202262 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1391345 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1093737 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1393365 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1637772 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1424542 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1548401 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1400001 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1628462 (Python Code)

Max Activating Token Index: 928

Text #13

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1482829 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7557. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1419084 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1456728 (Python Code)

Max Activating Token Index: 352

Text #17

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1531300 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7052. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1551339 (Python Code)

Max Activating Token Index: 614