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

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

Neuron 4388 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0594. Min Range: -1.0594

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1600963 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 1.0594. Min Range: -1.0594

Max Act: 1.0136. Min Act: 0.0000

Data Index: 1435976 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.9077. Min Act: 0.0000

Data Index: 1514713 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8703. Min Act: 0.0001

Data Index: 1399707 (Python Code)

Max Activating Token Index: 872

Text #4

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.9121. Min Act: 0.0000

Data Index: 1500861 (Python Code)

Max Activating Token Index: 783

Text #5

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1424532 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8558. Min Act: 0.0001

Data Index: 1452524 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8281. Min Act: 0.0000

Data Index: 1524006 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.9439. Min Act: 0.0000

Data Index: 1573277 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7641. Min Act: 0.0001

Data Index: 1461395 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1479878 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7737. Min Act: 0.0000

Data Index: 1480168 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7461. Min Act: 0.0000

Data Index: 1469435 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1370208 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7352. Min Act: 0.0001

Data Index: 1553369 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7373. Min Act: 0.0000

Data Index: 1387807 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7497. Min Act: 0.0000

Data Index: 1568870 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.8057. Min Act: -0.0000

Data Index: 241315 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6818. Min Act: 0.0001

Data Index: 1442783 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6823. Min Act: 0.0000

Data Index: 1382597 (Python Code)

Max Activating Token Index: 483