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

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

Neuron 3246 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.3908. Min Act: -0.0002

Data Index: 1568621 (Python Code)

Max Activating Token Index: 537

Text #1

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0432. Min Act: -0.0002

Data Index: 1426718 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1341. Min Act: -0.0002

Data Index: 1652529 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.2926. Min Act: -0.0002

Data Index: 1436126 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.2588. Min Act: -0.0002

Data Index: 1532226 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1752. Min Act: -0.0002

Data Index: 1421817 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1767. Min Act: -0.0002

Data Index: 1427817 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1651. Min Act: -0.0002

Data Index: 1428430 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0569. Min Act: -0.0002

Data Index: 1413660 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1353. Min Act: -0.0002

Data Index: 1460476 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0942. Min Act: -0.0002

Data Index: 1453374 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0468. Min Act: -0.0002

Data Index: 1493507 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1118. Min Act: -0.0002

Data Index: 1619786 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.8685. Min Act: -0.0002

Data Index: 1530828 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6795. Min Act: -0.0002

Data Index: 1556580 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0827. Min Act: -0.0002

Data Index: 1555612 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1364. Min Act: -0.0002

Data Index: 1564605 (Python Code)

Max Activating Token Index: 452

Text #17

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.9466. Min Act: -0.0002

Data Index: 1584499 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.0649. Min Act: -0.0002

Data Index: 1646435 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.1596. Min Act: -0.0002

Data Index: 1362371 (Python Code)

Max Activating Token Index: 669