Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2764 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.7055. Min Act: -0.0001
Data Index: 887355 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.5198. Min Act: -0.0001
Data Index: 613913 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.4000. Min Act: -0.0000
Data Index: 463629 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.2389. Min Act: -0.0001
Data Index: 156182 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.1607. Min Act: -0.0001
Data Index: 463041 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.2729. Min Act: -0.0001
Data Index: 411830 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.2163. Min Act: -0.0001
Data Index: 926577 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.0086. Min Act: -0.0001
Data Index: 1156607 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.8802. Min Act: -0.0001
Data Index: 119586 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.9619. Min Act: -0.0001
Data Index: 195154 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.1506. Min Act: -0.0000
Data Index: 937227 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.0056. Min Act: -0.0001
Data Index: 415324 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.8898. Min Act: -0.0001
Data Index: 312707 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.7598. Min Act: -0.0001
Data Index: 735026 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7055. Min Range: -2.7055
Max Act: 2.1753. Min Act: -0.0001
Data Index: 1128102 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.8432. Min Act: -0.0000
Data Index: 934656 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.7081. Min Act: -0.0001
Data Index: 401316 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.8113. Min Act: -0.0001
Data Index: 246522 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.8091. Min Act: -0.0001
Data Index: 410992 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7055. Min Range: -2.7055
Max Act: 1.7921. Min Act: -0.0001
Data Index: 1250688 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19