Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2658 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.9753. Min Range: -3.9753
Max Act: 3.9753. Min Act: -0.0001
Data Index: 1556547 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9753. Min Range: -3.9753
Max Act: 3.1636. Min Act: -0.0001
Data Index: 1634757 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.9036. Min Act: -0.0001
Data Index: 1624135 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9753. Min Range: -3.9753
Max Act: 3.0399. Min Act: -0.0001
Data Index: 1525099 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.9571. Min Act: -0.0001
Data Index: 1410048 (Python Code)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.2301. Min Act: -0.0001
Data Index: 1562792 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.3795. Min Act: -0.0001
Data Index: 1628025 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.8799. Min Act: -0.0001
Data Index: 1435568 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.8242. Min Act: -0.0001
Data Index: 1402166 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.5073. Min Act: -0.0001
Data Index: 1506076 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.2455. Min Act: -0.0001
Data Index: 1513700 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.5003. Min Act: -0.0001
Data Index: 1382070 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.4995. Min Act: -0.0001
Data Index: 1590484 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.7217. Min Act: -0.0001
Data Index: 1611033 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.5756. Min Act: -0.0001
Data Index: 1459831 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.4793. Min Act: -0.0001
Data Index: 1406155 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.6937. Min Act: -0.0001
Data Index: 1531683 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.5727. Min Act: -0.0001
Data Index: 1476470 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.3736. Min Act: -0.0001
Data Index: 1475358 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9753. Min Range: -3.9753
Max Act: 2.5486. Min Act: -0.0001
Data Index: 1505372 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19