Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1594093 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1381801 (Python Code)

Max Activating Token Index: 718

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1579909 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1563649 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1648313 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1588145 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1480310 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1584481 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1486673 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1446237 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2671. Min Act: -0.0001

Data Index: 1642837 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1520380 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1522274 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1519759 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1557634 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1438625 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1572412 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1414453 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1572355 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1366574 (Python Code)

Max Activating Token Index: 402