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

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

Neuron 13 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.7699. Min Act: -0.0000

Data Index: 1568230 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.5841. Min Act: -0.0000

Data Index: 1484621 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.1266. Min Act: -0.0000

Data Index: 1426634 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.1513. Min Act: -0.0000

Data Index: 1514324 (Python Code)

Max Activating Token Index: 703

Text #4

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.0327. Min Act: -0.0000

Data Index: 1563513 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1514044 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.1390. Min Act: -0.0000

Data Index: 1529449 (Python Code)

Max Activating Token Index: 717

Text #7

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.9308. Min Act: -0.0000

Data Index: 1400672 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 3.7699. Min Range: -3.7699

Max Act: 3.2884. Min Act: -0.0000

Data Index: 1431188 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.9785. Min Act: -0.0000

Data Index: 1504649 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.9785. Min Act: -0.0000

Data Index: 1517952 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.9806. Min Act: -0.0000

Data Index: 1656361 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.6049. Min Act: -0.0000

Data Index: 1440976 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.7386. Min Act: -0.0000

Data Index: 1383742 (Python Code)

Max Activating Token Index: 391

Text #14

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.5880. Min Act: -0.0000

Data Index: 1555757 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.7257. Min Act: -0.0000

Data Index: 1424438 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.8140. Min Act: -0.0000

Data Index: 1598023 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.5048. Min Act: -0.0000

Data Index: 1390215 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.7375. Min Act: -0.0000

Data Index: 1592693 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 3.7699. Min Range: -3.7699

Max Act: 2.5852. Min Act: -0.0000

Data Index: 1652055 (Python Code)

Max Activating Token Index: 577