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

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

Neuron 5276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3142. Min Range: -3.3142

Max Act: 3.3142. Min Act: -0.0000

Data Index: 1530716 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 3.3142. Min Range: -3.3142

Max Act: 3.1407. Min Act: -0.0000

Data Index: 1517128 (Python Code)

Max Activating Token Index: 419

Text #2

Max Range: 3.3142. Min Range: -3.3142

Max Act: 3.0473. Min Act: -0.0000

Data Index: 1628960 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.7238. Min Act: -0.0000

Data Index: 1386728 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.8728. Min Act: -0.0000

Data Index: 1433773 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1621853 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.7681. Min Act: -0.0000

Data Index: 1384516 (Python Code)

Max Activating Token Index: 485

Text #7

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.5068. Min Act: -0.0000

Data Index: 1630034 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.5960. Min Act: -0.0000

Data Index: 1481180 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.5519. Min Act: -0.0000

Data Index: 1468205 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1631424 (Python Code)

Max Activating Token Index: 240

Text #11

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1405380 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.2851. Min Act: -0.0000

Data Index: 1506185 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.5162. Min Act: -0.0000

Data Index: 1508054 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.4477. Min Act: -0.0000

Data Index: 1580646 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.3200. Min Act: -0.0000

Data Index: 1481435 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.2836. Min Act: -0.0000

Data Index: 1571895 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.3889. Min Act: -0.0000

Data Index: 1626218 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.1394. Min Act: -0.0000

Data Index: 1514362 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 3.3142. Min Range: -3.3142

Max Act: 2.1241. Min Act: -0.0000

Data Index: 1527839 (Python Code)

Max Activating Token Index: 672