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

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

Neuron 4961 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4254. Min Range: -5.4254

Max Act: 5.0655. Min Act: -0.0000

Data Index: 1366883 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 5.4254. Min Range: -5.4254

Max Act: 5.4254. Min Act: -0.0000

Data Index: 1458428 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.9021. Min Act: -0.0000

Data Index: 1639862 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 5.4254. Min Range: -5.4254

Max Act: 5.1233. Min Act: -0.0000

Data Index: 1501837 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.8482. Min Act: -0.0000

Data Index: 1652526 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.7515. Min Act: -0.0000

Data Index: 1606599 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.5315. Min Act: -0.0000

Data Index: 1398353 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.6718. Min Act: -0.0000

Data Index: 1464389 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.6054. Min Act: -0.0000

Data Index: 1632806 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.3914. Min Act: -0.0000

Data Index: 1505514 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.3783. Min Act: -0.0000

Data Index: 1512032 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1406751 (Python Code)

Max Activating Token Index: 464

Text #12

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.5559. Min Act: -0.0000

Data Index: 1655168 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.7185. Min Act: -0.0000

Data Index: 1517057 (Python Code)

Max Activating Token Index: 843

Text #14

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.5264. Min Act: -0.0000

Data Index: 1486955 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.6445. Min Act: -0.0000

Data Index: 1365227 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.4195. Min Act: -0.0000

Data Index: 1399677 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.4072. Min Act: -0.0000

Data Index: 1452598 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.1539. Min Act: -0.0000

Data Index: 1403355 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 5.4254. Min Range: -5.4254

Max Act: 4.5203. Min Act: -0.0000

Data Index: 1413726 (Python Code)

Max Activating Token Index: 657