Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6053 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.5563. Min Act: -0.1700
Data Index: 1126446 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.9626. Min Act: -0.1700
Data Index: 6919865 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 7537129 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6813. Min Act: -0.1700
Data Index: 8187813 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6501. Min Act: -0.1700
Data Index: 6604984 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6501. Min Act: -0.1700
Data Index: 3692343 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6501. Min Act: -0.1700
Data Index: 5121307 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6501. Min Act: -0.1700
Data Index: 4154792 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5876. Min Act: -0.1700
Data Index: 3157223 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.6188. Min Act: -0.1700
Data Index: 5952622 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5876. Min Act: -0.1700
Data Index: 2221121 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5876. Min Act: -0.1700
Data Index: 2205460 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5876. Min Act: -0.1700
Data Index: 7851175 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5876. Min Act: -0.1700
Data Index: 2685832 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5563. Min Act: -0.1700
Data Index: 1816207 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5251. Min Act: -0.1700
Data Index: 767191 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.5251. Min Act: -0.1700
Data Index: 6286939 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.4626. Min Act: -0.1700
Data Index: 6187201 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.4938. Min Act: -0.1700
Data Index: 831981 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5563. Min Range: -6.5563
Max Act: 5.4938. Min Act: -0.1700
Data Index: 247048 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19