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

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

Neuron 4546 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1533169 (Python Code)

Max Activating Token Index: 917

Text #1

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1563343 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1610452 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1372016 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1470706 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1456509 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1617785 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1600184 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1427710 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1420965 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1428480 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1495680 (Python Code)

Max Activating Token Index: 279

Text #12

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1620279 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1593154 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1424008 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1391772 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1483278 (Python Code)

Max Activating Token Index: 468

Text #17

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1466263 (Python Code)

Max Activating Token Index: 538

Text #18

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1415360 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1606459 (Python Code)

Max Activating Token Index: 976