Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5854 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.4814. Min Act: -0.1700
Data Index: 1179758 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.3876. Min Act: -0.1700
Data Index: 550946 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2939. Min Act: -0.1700
Data Index: 2050458 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2626. Min Act: -0.1700
Data Index: 4590636 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2001. Min Act: -0.1700
Data Index: 2835073 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1689. Min Act: -0.1700
Data Index: 1977908 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2001. Min Act: -0.1700
Data Index: 5634039 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1689. Min Act: -0.1700
Data Index: 3972342 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1689. Min Act: -0.1700
Data Index: 942589 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 6008831 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 6485348 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 866022 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 2050457 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 1977909 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 883777 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 6008830 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0126. Min Act: -0.1700
Data Index: 1252777 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4814. Min Range: -4.4814
Max Act: 3.9813. Min Act: -0.1700
Data Index: 942590 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4814. Min Range: -4.4814
Max Act: 3.9501. Min Act: -0.1700
Data Index: 5142992 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4814. Min Range: -4.4814
Max Act: 3.9813. Min Act: -0.1700
Data Index: 198135 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19