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

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

Neuron 3313 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: 0.5657. Min Range: -0.5657

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1513910 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1525812 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1422262 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1531713 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1434618 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1482299 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1552958 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1537738 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1522117 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1414846 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1656665 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1548413 (Python Code)

Max Activating Token Index: 903

Text #12

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1436835 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1571105 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1360739 (Python Code)

Max Activating Token Index: 739

Text #15

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1562708 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1464156 (Python Code)

Max Activating Token Index: 571

Text #17

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1439115 (Python Code)

Max Activating Token Index: 446

Text #18

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1479897 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1555326 (Python Code)

Max Activating Token Index: 725