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

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

Neuron 559 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: 6.0747. Min Range: -6.0747

Max Act: 6.0747. Min Act: -0.0000

Data Index: 1479563 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.9428. Min Act: -0.0000

Data Index: 1545356 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.5526. Min Act: -0.0000

Data Index: 1620880 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.2231. Min Act: -0.0000

Data Index: 1426928 (Python Code)

Max Activating Token Index: 519

Text #4

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.3492. Min Act: -0.0000

Data Index: 1555970 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.3548. Min Act: -0.0000

Data Index: 1382701 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.3593. Min Act: -0.0000

Data Index: 1517766 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.5377. Min Act: -0.0000

Data Index: 1577753 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.1228. Min Act: -0.0000

Data Index: 1447247 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.3048. Min Act: -0.0000

Data Index: 1427293 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.2377. Min Act: -0.0000

Data Index: 1514716 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.2380. Min Act: -0.0000

Data Index: 1391375 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.2405. Min Act: -0.0000

Data Index: 1479664 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 6.0747. Min Range: -6.0747

Max Act: 4.8323. Min Act: -0.0000

Data Index: 1391421 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.0254. Min Act: -0.0000

Data Index: 1466526 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.2144. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.1839. Min Act: -0.0000

Data Index: 1480897 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.1925. Min Act: -0.0000

Data Index: 1566205 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 6.0747. Min Range: -6.0747

Max Act: 5.0191. Min Act: -0.0000

Data Index: 1607168 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 6.0747. Min Range: -6.0747

Max Act: 4.8079. Min Act: -0.0000

Data Index: 1656430 (Python Code)

Max Activating Token Index: 862