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

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

Neuron 3515 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.9504. Min Act: -0.0000

Data Index: 1641012 (Python Code)

Max Activating Token Index: 685

Text #1

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.8834. Min Act: -0.0000

Data Index: 1569328 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1372056 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.7484. Min Act: -0.0000

Data Index: 1518033 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.5528. Min Act: -0.0000

Data Index: 1423049 (Python Code)

Max Activating Token Index: 504

Text #5

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1378293 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1525390 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1447426 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1461902 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1485944 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1494027 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1496068 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1608974 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1498515 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1505747 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1523026 (Python Code)

Max Activating Token Index: 713

Text #16

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1597492 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1457333 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1643058 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 1.9504. Min Range: -1.9504

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1427615 (Python Code)

Max Activating Token Index: 340