Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.9876. Min Act: -0.1700
Data Index: 8681131 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.4251. Min Act: -0.1700
Data Index: 5533760 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.3626. Min Act: -0.1700
Data Index: 8027821 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.3939. Min Act: -0.1700
Data Index: 5081822 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.2376. Min Act: -0.1700
Data Index: 3958614 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.2376. Min Act: -0.1700
Data Index: 8092045 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1751. Min Act: -0.1700
Data Index: 4390242 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1751. Min Act: -0.1700
Data Index: 1358312 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1751. Min Act: -0.1700
Data Index: 3766821 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1439. Min Act: -0.1700
Data Index: 2369647 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1126. Min Act: -0.1700
Data Index: 6462524 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.1126. Min Act: -0.1700
Data Index: 1351466 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4927656 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8241753 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0501. Min Act: -0.1700
Data Index: 4770983 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 7377610 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0189. Min Act: -0.1700
Data Index: 1293999 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9876. Min Range: -6.9876
Max Act: 5.9876. Min Act: -0.1700
Data Index: 6029557 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9876. Min Range: -6.9876
Max Act: 6.0189. Min Act: -0.1700
Data Index: 4234882 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9876. Min Range: -6.9876
Max Act: 5.9876. Min Act: -0.1700
Data Index: 909594 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19