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

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

Neuron 2380 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1456843 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1578493 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1481043 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1537763 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.3103. Min Act: -0.0000

Data Index: 1363401 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1554. Min Act: 0.0000

Data Index: 1420859 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1465662 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1627040 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0918. Min Act: 0.0000

Data Index: 1463372 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1539673 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1464469 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1124. Min Act: 0.0001

Data Index: 1457009 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1378098 (Python Code)

Max Activating Token Index: 450

Text #13

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1510656 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1590802 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1579122 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1339. Min Act: 0.0000

Data Index: 1552394 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1533211 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1520081 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 1.8807. Min Range: -1.8807

Max Act: 0.9751. Min Act: 0.0000

Data Index: 1459523 (Python Code)

Max Activating Token Index: 823