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

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

Neuron 4414 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: 1.7882. Min Range: -1.7882

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1556145 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1392903 (Python Code)

Max Activating Token Index: 331

Text #2

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1655904 (Python Code)

Max Activating Token Index: 691

Text #3

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6719. Min Act: -0.0000

Data Index: 1486190 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1434722 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1540058 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1650607 (Python Code)

Max Activating Token Index: 759

Text #7

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1548223 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.5384. Min Act: -0.0000

Data Index: 1599621 (Python Code)

Max Activating Token Index: 393

Text #9

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1572466 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1559985 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1601041 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1423018 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1568872 (Python Code)

Max Activating Token Index: 199

Text #14

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1652446 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1547019 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1381957 (Python Code)

Max Activating Token Index: 286

Text #17

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1361657 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1511821 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1413358 (Python Code)

Max Activating Token Index: 461