Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.8180. Min Act: -0.1700
Data Index: 1870809 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.8493. Min Act: -0.1700
Data Index: 249068 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.8180. Min Act: -0.1700
Data Index: 3683287 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7555. Min Act: -0.1700
Data Index: 3562882 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7868. Min Act: -0.1700
Data Index: 814864 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7868. Min Act: -0.1700
Data Index: 2729246 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7868. Min Act: -0.1700
Data Index: 5370500 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7868. Min Act: -0.1700
Data Index: 1574817 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7555. Min Act: -0.1700
Data Index: 7206335 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7868. Min Act: -0.1700
Data Index: 1387760 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.7555. Min Act: -0.1700
Data Index: 645120 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.6930. Min Act: -0.1700
Data Index: 7348435 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.6618. Min Act: -0.1700
Data Index: 5785458 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.6305. Min Act: -0.1700
Data Index: 6909567 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5993. Min Act: -0.1700
Data Index: 3365778 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5680. Min Act: -0.1700
Data Index: 7511102 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5680. Min Act: -0.1700
Data Index: 8032225 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5680. Min Act: -0.1700
Data Index: 3870986 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5993. Min Act: -0.1700
Data Index: 1279025 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8493. Min Range: -5.8493
Max Act: 5.5368. Min Act: -0.1700
Data Index: 3967769 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19