Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4246 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.7858. Min Act: -0.0001
Data Index: 1361854 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.6784. Min Act: -0.0001
Data Index: 1362218 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.4199. Min Act: -0.0001
Data Index: 1505103 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.4865. Min Act: -0.0001
Data Index: 1573119 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.5624. Min Act: -0.0001
Data Index: 1440630 (Python Code)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.6470. Min Act: -0.0001
Data Index: 1565903 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.4403. Min Act: -0.0001
Data Index: 1545619 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.3818. Min Act: -0.0001
Data Index: 1459000 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.7081. Min Act: -0.0001
Data Index: 1433834 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.2951. Min Act: -0.0001
Data Index: 1615169 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.6003. Min Act: -0.0001
Data Index: 1535250 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.3538. Min Act: -0.0001
Data Index: 1364309 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.4847. Min Act: -0.0001
Data Index: 1364752 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.7257. Min Act: -0.0001
Data Index: 1546220 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.2491. Min Act: -0.0001
Data Index: 1414022 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.5800. Min Act: -0.0001
Data Index: 1504633 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.3896. Min Act: -0.0001
Data Index: 1467645 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7858. Min Range: -1.7858
Max Act: 0.9698. Min Act: -0.0001
Data Index: 1478568 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.7054. Min Act: -0.0001
Data Index: 1495579 (Python Code)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7858. Min Range: -1.7858
Max Act: 1.6051. Min Act: -0.0001
Data Index: 1510069 (Python Code)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19