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

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

Neuron 4774 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5814. Min Act: -0.0000

Data Index: 1369986 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5682. Min Act: -0.0000

Data Index: 1596029 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5568. Min Act: -0.0000

Data Index: 1563725 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5462. Min Act: -0.0000

Data Index: 1391822 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5484. Min Act: -0.0000

Data Index: 1451735 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5507. Min Act: -0.0000

Data Index: 1419473 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5339. Min Act: -0.0000

Data Index: 1424538 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5184. Min Act: -0.0000

Data Index: 1471662 (Python Code)

Max Activating Token Index: 663

Text #8

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.3822. Min Act: -0.0000

Data Index: 1546271 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5245. Min Act: -0.0000

Data Index: 1499177 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.6024. Min Act: -0.0000

Data Index: 1523298 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4377. Min Act: -0.0000

Data Index: 1460748 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4266. Min Act: -0.0000

Data Index: 1546132 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.1597. Min Act: -0.0000

Data Index: 1472429 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4130. Min Act: -0.0000

Data Index: 1558746 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1446525 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1494121 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4141. Min Act: -0.0000

Data Index: 1444583 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1570345 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 3.6024. Min Range: -3.6024

Max Act: 3.4190. Min Act: -0.0000

Data Index: 1404001 (Python Code)

Max Activating Token Index: 756