Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3409 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.4771. Min Act: -0.0001
Data Index: 1088339 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.2053. Min Act: -0.0001
Data Index: 649525 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.0674. Min Act: -0.0001
Data Index: 694118 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.1575. Min Act: -0.0001
Data Index: 98333 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.1745. Min Act: -0.0001
Data Index: 685 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.0287. Min Act: -0.0001
Data Index: 1110433 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.1253. Min Act: -0.0001
Data Index: 148549 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.1372. Min Act: -0.0001
Data Index: 467747 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.1494. Min Act: -0.0001
Data Index: 54534 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.0415. Min Act: -0.0001
Data Index: 429132 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.0720. Min Act: -0.0001
Data Index: 648865 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9654. Min Act: -0.0001
Data Index: 1197237 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9154. Min Act: -0.0001
Data Index: 175126 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4771. Min Range: -1.4771
Max Act: 1.0585. Min Act: -0.0001
Data Index: 325276 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.8724. Min Act: -0.0001
Data Index: 1080372 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9874. Min Act: -0.0001
Data Index: 427783 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9981. Min Act: -0.0001
Data Index: 341840 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9879. Min Act: -0.0001
Data Index: 134650 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.9484. Min Act: -0.0001
Data Index: 888652 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4771. Min Range: -1.4771
Max Act: 0.8708. Min Act: -0.0001
Data Index: 1314781 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19