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

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

Neuron 3169 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1384345 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8011. Min Act: -0.0001

Data Index: 1401660 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1413556 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1514266 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7662. Min Act: -0.0001

Data Index: 1380677 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7578. Min Act: -0.0001

Data Index: 1489214 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7806. Min Act: -0.0001

Data Index: 1482678 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1464191 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1581171 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1566397 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7764. Min Act: -0.0001

Data Index: 1442158 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1403443 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1563097 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6723. Min Act: -0.0001

Data Index: 1598312 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1446599 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1568411 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1483935 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1516151 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1408438 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1431526 (Python Code)

Max Activating Token Index: 694