Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1904 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6558. Min Act: -0.0006

Data Index: 1422476 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6329. Min Act: -0.0006

Data Index: 1579647 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5963. Min Act: -0.0006

Data Index: 1420060 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5944. Min Act: -0.0006

Data Index: 1537361 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5665. Min Act: -0.0006

Data Index: 1605110 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5797. Min Act: -0.0006

Data Index: 1557059 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5574. Min Act: -0.0006

Data Index: 1572655 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5732. Min Act: -0.0006

Data Index: 1397528 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5655. Min Act: -0.0006

Data Index: 1647372 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5806. Min Act: -0.0006

Data Index: 1572050 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5604. Min Act: -0.0006

Data Index: 1485126 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5544. Min Act: -0.0006

Data Index: 1463296 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5352. Min Act: -0.0006

Data Index: 1652388 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5500. Min Act: -0.0006

Data Index: 1482660 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5314. Min Act: -0.0006

Data Index: 1529016 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5296. Min Act: -0.0006

Data Index: 1543963 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5619. Min Act: -0.0006

Data Index: 1517751 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5597. Min Act: -0.0006

Data Index: 1476647 (Python Code)

Max Activating Token Index: 368

Text #18

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5781. Min Act: -0.0006

Data Index: 1418819 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5536. Min Act: -0.0006

Data Index: 1438894 (Python Code)

Max Activating Token Index: 641