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

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

Neuron 1440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.9540. Min Act: -0.0000

Data Index: 1410146 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.9907. Min Act: -0.0001

Data Index: 1370527 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.8260. Min Act: -0.0000

Data Index: 1533971 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.8958. Min Act: -0.0000

Data Index: 1623407 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.8244. Min Act: -0.0000

Data Index: 1450822 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6772. Min Act: -0.0000

Data Index: 1570306 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.8965. Min Act: -0.0000

Data Index: 1419881 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.7806. Min Act: -0.0000

Data Index: 1469028 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.7790. Min Act: -0.0000

Data Index: 1531276 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.8621. Min Act: -0.0000

Data Index: 1544333 (Python Code)

Max Activating Token Index: 76

Text #10

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6890. Min Act: -0.0000

Data Index: 1362371 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6370. Min Act: -0.0000

Data Index: 1492007 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.5349. Min Act: -0.0000

Data Index: 1533250 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.7793. Min Act: -0.0000

Data Index: 1487850 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.4985. Min Act: -0.0000

Data Index: 1469632 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6300. Min Act: -0.0000

Data Index: 1415494 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6228. Min Act: -0.0000

Data Index: 1370178 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.6361. Min Act: -0.0001

Data Index: 1436580 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.4625. Min Act: -0.0000

Data Index: 1395688 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 2.9907. Min Range: -2.9907

Max Act: 2.4362. Min Act: -0.0000

Data Index: 1507147 (Python Code)

Max Activating Token Index: 484