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

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

Neuron 3034 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6597. Min Range: -5.6597

Max Act: 5.6597. Min Act: -0.0000

Data Index: 1413849 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 5.6597. Min Range: -5.6597

Max Act: 4.6025. Min Act: -0.0000

Data Index: 1390640 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 5.6597. Min Range: -5.6597

Max Act: 4.3153. Min Act: -0.0000

Data Index: 1590409 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 5.6597. Min Range: -5.6597

Max Act: 4.0894. Min Act: -0.0000

Data Index: 1538823 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.7983. Min Act: -0.0000

Data Index: 1415195 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.5621. Min Act: -0.0000

Data Index: 1475158 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.6310. Min Act: -0.0000

Data Index: 1399038 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.2303. Min Act: -0.0000

Data Index: 1411711 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.1878. Min Act: -0.0000

Data Index: 1418801 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.1102. Min Act: -0.0000

Data Index: 1607313 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.9684. Min Act: -0.0000

Data Index: 1460631 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.0510. Min Act: -0.0000

Data Index: 1464614 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.0240. Min Act: -0.0000

Data Index: 1596279 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1454782 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.9367. Min Act: -0.0000

Data Index: 1394652 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 5.6597. Min Range: -5.6597

Max Act: 3.0419. Min Act: -0.0000

Data Index: 1385657 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.7379. Min Act: -0.0000

Data Index: 1648562 (Python Code)

Max Activating Token Index: 502

Text #17

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.7008. Min Act: 0.0000

Data Index: 1497028 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.7081. Min Act: 0.0001

Data Index: 1627295 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 5.6597. Min Range: -5.6597

Max Act: 2.9065. Min Act: -0.0000

Data Index: 1372960 (Python Code)

Max Activating Token Index: 863