Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2617 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.6793. Min Act: -0.0001
Data Index: 1477073 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.5648. Min Act: -0.0001
Data Index: 1470349 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.1898. Min Act: -0.0001
Data Index: 1597831 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.1663. Min Act: -0.0001
Data Index: 1600616 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.2032. Min Act: -0.0001
Data Index: 1656431 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0580. Min Act: -0.0001
Data Index: 1534994 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0498. Min Act: -0.0001
Data Index: 1626844 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0730. Min Act: -0.0001
Data Index: 1556302 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0492. Min Act: -0.0001
Data Index: 1488674 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0072. Min Act: -0.0001
Data Index: 1469848 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9606. Min Act: -0.0001
Data Index: 1478104 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0189. Min Act: -0.0001
Data Index: 1401418 (Python Code)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0119. Min Act: -0.0001
Data Index: 1533600 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9778. Min Act: -0.0001
Data Index: 1489723 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6793. Min Range: -1.6793
Max Act: 1.0052. Min Act: -0.0001
Data Index: 1467905 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9478. Min Act: -0.0001
Data Index: 1624846 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9655. Min Act: -0.0001
Data Index: 1391154 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9827. Min Act: -0.0001
Data Index: 1411452 (Python Code)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9539. Min Act: -0.0001
Data Index: 1439420 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6793. Min Range: -1.6793
Max Act: 0.9441. Min Act: -0.0001
Data Index: 1604243 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19