Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 832 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0878. Min Act: -0.0001
Data Index: 421962 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0843. Min Act: -0.0001
Data Index: 661051 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0815. Min Act: -0.0001
Data Index: 1066378 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0729. Min Act: -0.0001
Data Index: 1080085 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0815. Min Act: -0.0001
Data Index: 527599 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0779. Min Act: -0.0001
Data Index: 1164809 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0764. Min Act: -0.0001
Data Index: 809781 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0757. Min Act: -0.0001
Data Index: 198468 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0717. Min Act: -0.0001
Data Index: 1282793 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0761. Min Act: -0.0001
Data Index: 1234033 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0759. Min Act: -0.0001
Data Index: 268513 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0718. Min Act: -0.0001
Data Index: 937878 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0711. Min Act: -0.0001
Data Index: 114643 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0706. Min Act: -0.0001
Data Index: 6086 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0732. Min Act: -0.0001
Data Index: 1430048 (Python Code)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0706. Min Act: -0.0001
Data Index: 1121605 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0718. Min Act: -0.0001
Data Index: 1058945 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0697. Min Act: -0.0001
Data Index: 658152 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0730. Min Act: -0.0001
Data Index: 463914 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0878. Min Range: -0.0878
Max Act: 0.0700. Min Act: -0.0001
Data Index: 1590132 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19