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

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

Neuron 104 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1579493 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1369058 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1416324 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2849. Min Act: -0.0001

Data Index: 1603926 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1476611 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1379277 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1423644 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1553504 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1572348 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1368053 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1373116 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1498918 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1573290 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1462214 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2462. Min Act: -0.0001

Data Index: 1423198 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1515193 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1555567 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1361115 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1454426 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1625367 (Python Code)

Max Activating Token Index: 26