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

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

Neuron 3771 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1602342 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1567601 (Python Code)

Max Activating Token Index: 419

Text #2

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1427094 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1655919 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1651023 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1391386 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1476499 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1422483 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1620144 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1375044 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1474480 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1438394 (Python Code)

Max Activating Token Index: 242

Text #12

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1394245 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1590173 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1577568 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1410313 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1641550 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1380424 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1473716 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1589446 (Python Code)

Max Activating Token Index: 652