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

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

Neuron 3300 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.5335. Min Act: 0.0001

Data Index: 1472191 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1599744 (Python Code)

Max Activating Token Index: 515

Text #2

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1555795 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1527678 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1476110 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1551970 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1447794 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1523024 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1084. Min Act: 0.0000

Data Index: 1528766 (Python Code)

Max Activating Token Index: 377

Text #9

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1391544 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0786. Min Act: -0.0000

Data Index: 937897 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0706. Min Act: 0.0000

Data Index: 1640173 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1513090 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0272. Min Act: 0.0000

Data Index: 1462068 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1371685 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 1.5335. Min Range: -1.5335

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1492917 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 1.5335. Min Range: -1.5335

Max Act: 0.9570. Min Act: 0.0000

Data Index: 1627704 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 1.5335. Min Range: -1.5335

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1556815 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 1.5335. Min Range: -1.5335

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1517437 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 1.5335. Min Range: -1.5335

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1550176 (Python Code)

Max Activating Token Index: 629