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

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

Neuron 5142 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1417162 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1537545 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1614886 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1482611 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1532263 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1595259 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1381278 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1532652 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1405762 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1640819 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1571641 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1600371 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1618481 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1468135 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1530524 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1504620 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1535593 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1546076 (Python Code)

Max Activating Token Index: 683

Text #18

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1548671 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1632683 (Python Code)

Max Activating Token Index: 458