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

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

Neuron 4837 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0795. Min Range: -3.0795

Max Act: 3.0795. Min Act: -0.0000

Data Index: 1163420 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.7108. Min Act: -0.0001

Data Index: 1613639 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.4112. Min Act: -0.0001

Data Index: 477919 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.3918. Min Act: -0.0000

Data Index: 1556373 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.2607. Min Act: -0.0001

Data Index: 1648529 (Python Code)

Max Activating Token Index: 393

Text #5

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.4759. Min Act: -0.0001

Data Index: 576543 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.3560. Min Act: -0.0000

Data Index: 170671 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.0886. Min Act: -0.0000

Data Index: 1492777 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.1207. Min Act: -0.0001

Data Index: 43652 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.0886. Min Act: -0.0000

Data Index: 1393914 (Python Code)

Max Activating Token Index: 708

Text #10

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.0787. Min Act: -0.0000

Data Index: 1437121 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.0723. Min Act: -0.0001

Data Index: 1578903 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.1505. Min Act: -0.0001

Data Index: 1572766 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.0108. Min Act: -0.0000

Data Index: 2746 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.0795. Min Range: -3.0795

Max Act: 2.1216. Min Act: -0.0000

Data Index: 979450 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.0795. Min Range: -3.0795

Max Act: 1.9860. Min Act: -0.0000

Data Index: 859414 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 3.0795. Min Range: -3.0795

Max Act: 1.9807. Min Act: -0.0000

Data Index: 640497 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 3.0795. Min Range: -3.0795

Max Act: 1.9646. Min Act: -0.0000

Data Index: 1132485 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 3.0795. Min Range: -3.0795

Max Act: 1.8600. Min Act: -0.0000

Data Index: 734452 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.0795. Min Range: -3.0795

Max Act: 1.9467. Min Act: -0.0001

Data Index: 1203715 (C4 (Web Text))

Max Activating Token Index: 246