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

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

Neuron 4559 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: 1.1439. Min Range: -1.1439

Max Act: 1.1439. Min Act: -0.0001

Data Index: 1585890 (Python Code)

Max Activating Token Index: 292

Text #1

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1444674 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1424088 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.9628. Min Act: -0.0001

Data Index: 1383986 (Python Code)

Max Activating Token Index: 362

Text #4

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1455844 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.9173. Min Act: -0.0001

Data Index: 1389484 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1510151 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1396082 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1517895 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8024. Min Act: -0.0001

Data Index: 1414117 (Python Code)

Max Activating Token Index: 598

Text #10

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7690. Min Act: -0.0001

Data Index: 1481418 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1486437 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8534. Min Act: -0.0001

Data Index: 1387845 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7204. Min Act: -0.0001

Data Index: 1460453 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1449829 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8025. Min Act: -0.0001

Data Index: 1469524 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1405680 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7028. Min Act: -0.0001

Data Index: 1547904 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.6958. Min Act: -0.0001

Data Index: 1441454 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1606721 (Python Code)

Max Activating Token Index: 782