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

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

Neuron 1193 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: 2.8795. Min Range: -2.8795

Max Act: 2.8795. Min Act: -0.0000

Data Index: 1588708 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.7363. Min Act: -0.0000

Data Index: 1500395 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.5682. Min Act: -0.0000

Data Index: 1404945 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1585314 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1389788 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.3294. Min Act: -0.0000

Data Index: 1562953 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1570897 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.1481. Min Act: -0.0000

Data Index: 1418390 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.2128. Min Act: -0.0000

Data Index: 1520542 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 2.8795. Min Range: -2.8795

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1504552 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.1374. Min Act: -0.0000

Data Index: 1406470 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1389025 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1385748 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1476292 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.1791. Min Act: -0.0000

Data Index: 1507902 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0498. Min Act: -0.0000

Data Index: 1451079 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0485. Min Act: -0.0000

Data Index: 1498093 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0403. Min Act: -0.0000

Data Index: 1488194 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 2.8795. Min Range: -2.8795

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1465888 (Python Code)

Max Activating Token Index: 714

Text #19

Max Range: 2.8795. Min Range: -2.8795

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1549455 (Python Code)

Max Activating Token Index: 338