Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2073 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5180. Min Range: -2.5180
Max Act: 2.5180. Min Act: -0.0001
Data Index: 1424227 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5180. Min Range: -2.5180
Max Act: 2.1846. Min Act: -0.0001
Data Index: 1460879 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5180. Min Range: -2.5180
Max Act: 2.3296. Min Act: -0.0001
Data Index: 1481279 (Python Code)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5180. Min Range: -2.5180
Max Act: 2.0097. Min Act: -0.0001
Data Index: 1508068 (Python Code)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.8771. Min Act: -0.0001
Data Index: 1470934 (Python Code)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.8707. Min Act: -0.0001
Data Index: 1491976 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.8097. Min Act: -0.0001
Data Index: 1391016 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.7955. Min Act: -0.0001
Data Index: 1654919 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.8701. Min Act: -0.0001
Data Index: 1443743 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.6256. Min Act: -0.0001
Data Index: 1524683 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.6747. Min Act: -0.0001
Data Index: 1523250 (Python Code)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.6720. Min Act: -0.0001
Data Index: 1512554 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.7006. Min Act: -0.0001
Data Index: 1519215 (Python Code)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.7391. Min Act: -0.0001
Data Index: 1373487 (Python Code)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.6841. Min Act: -0.0001
Data Index: 1642880 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.6383. Min Act: -0.0001
Data Index: 1467251 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.5743. Min Act: -0.0001
Data Index: 1436738 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.5373. Min Act: -0.0001
Data Index: 1573091 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.5373. Min Act: -0.0001
Data Index: 1614858 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5180. Min Range: -2.5180
Max Act: 1.5373. Min Act: -0.0001
Data Index: 1503304 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19