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

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

Neuron 1112 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: 3.9889. Min Range: -3.9889

Max Act: 3.9889. Min Act: -0.0000

Data Index: 1572626 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.5958. Min Act: -0.0000

Data Index: 1496981 (Python Code)

Max Activating Token Index: 511

Text #2

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.6280. Min Act: -0.0000

Data Index: 1462917 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.2986. Min Act: -0.0000

Data Index: 1557703 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.2590. Min Act: -0.0000

Data Index: 1580811 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.1057. Min Act: -0.0000

Data Index: 418124 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.0596. Min Act: -0.0000

Data Index: 1496625 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.2043. Min Act: -0.0000

Data Index: 1540496 (Python Code)

Max Activating Token Index: 536

Text #8

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1447763 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.6341. Min Act: -0.0000

Data Index: 888658 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.0229. Min Act: -0.0000

Data Index: 1589800 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.9850. Min Act: -0.0000

Data Index: 404396 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.9268. Min Act: -0.0000

Data Index: 1408806 (Python Code)

Max Activating Token Index: 332

Text #13

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.8863. Min Act: -0.0000

Data Index: 1508675 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.8478. Min Act: -0.0000

Data Index: 1419707 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.7181. Min Act: -0.0000

Data Index: 1401289 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.5346. Min Act: -0.0000

Data Index: 1481360 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.8007. Min Act: -0.0000

Data Index: 1649006 (Python Code)

Max Activating Token Index: 859

Text #18

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.7796. Min Act: -0.0000

Data Index: 1416805 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 3.9889. Min Range: -3.9889

Max Act: 2.7714. Min Act: -0.0000

Data Index: 1593524 (Python Code)

Max Activating Token Index: 912