Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6876. Min Act: -0.1700
Data Index: 1157059 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6876. Min Act: -0.1700
Data Index: 2907141 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6563. Min Act: -0.1700
Data Index: 8225951 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6563. Min Act: -0.1700
Data Index: 6217813 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6250. Min Act: -0.1700
Data Index: 3603220 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6250. Min Act: -0.1700
Data Index: 1796165 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6250. Min Act: -0.1700
Data Index: 701464 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 6690596 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.6250. Min Act: -0.1700
Data Index: 5994092 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 3711817 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 461673 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 6606587 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 4999440 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 4057985 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 312909 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5937. Min Act: -0.1700
Data Index: 3618125 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5624. Min Act: -0.1700
Data Index: 2603175 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5624. Min Act: -0.1700
Data Index: 3525908 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5624. Min Act: -0.1700
Data Index: 2771193 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6876. Min Range: -3.6876
Max Act: 3.5624. Min Act: -0.1700
Data Index: 2870648 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19