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

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

Neuron 4615 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1646832 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1489654 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1478891 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1430800 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1538417 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1605075 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1565660 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1433322 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1545922 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1633126 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1414582 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1549409 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1562021 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1385185 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1381728 (Python Code)

Max Activating Token Index: 642

Text #15

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1601315 (Python Code)

Max Activating Token Index: 645

Text #16

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1398403 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1376794 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1484654 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1366753 (Python Code)

Max Activating Token Index: 445