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

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

Neuron 5881 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: 5.8662. Min Range: -5.8662

Max Act: 5.6828. Min Act: 0.0000

Data Index: 1431271 (Python Code)

Max Activating Token Index: 905

Text #1

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.6954. Min Act: 0.0000

Data Index: 1519615 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.8662. Min Act: 0.0000

Data Index: 1543477 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.5392. Min Act: -0.0000

Data Index: 1629549 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2217. Min Act: -0.0000

Data Index: 1406144 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.1321. Min Act: -0.0000

Data Index: 1627855 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2844. Min Act: -0.0000

Data Index: 1481124 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2452. Min Act: -0.0000

Data Index: 1490067 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2184. Min Act: -0.0000

Data Index: 1447401 (Python Code)

Max Activating Token Index: 116

Text #9

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.3688. Min Act: -0.0000

Data Index: 1433188 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 5.8662. Min Range: -5.8662

Max Act: 4.9568. Min Act: -0.0000

Data Index: 1517749 (Python Code)

Max Activating Token Index: 641

Text #11

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.3020. Min Act: 0.0000

Data Index: 1650480 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2956. Min Act: -0.0000

Data Index: 1409136 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 5.8662. Min Range: -5.8662

Max Act: 4.7439. Min Act: -0.0000

Data Index: 1426554 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 5.8662. Min Range: -5.8662

Max Act: 4.9141. Min Act: -0.0000

Data Index: 1472257 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.0475. Min Act: -0.0000

Data Index: 1414147 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.2442. Min Act: -0.0000

Data Index: 1456801 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.0323. Min Act: -0.0000

Data Index: 1422152 (Python Code)

Max Activating Token Index: 566

Text #18

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.0331. Min Act: -0.0000

Data Index: 1407308 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 5.8662. Min Range: -5.8662

Max Act: 5.0234. Min Act: -0.0000

Data Index: 1491255 (Python Code)

Max Activating Token Index: 523