Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5777 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.9009. Min Act: -0.1700
Data Index: 2828155 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.7759. Min Act: -0.1700
Data Index: 8667669 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.6509. Min Act: -0.1700
Data Index: 5892762 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.6509. Min Act: -0.1700
Data Index: 4760945 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.5884. Min Act: -0.1700
Data Index: 6869279 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.5884. Min Act: -0.1700
Data Index: 4617481 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.4634. Min Act: -0.1700
Data Index: 2529764 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.4634. Min Act: -0.1700
Data Index: 7627518 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.4009. Min Act: -0.1700
Data Index: 7636261 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.4009. Min Act: -0.1700
Data Index: 594492 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.3384. Min Act: -0.1700
Data Index: 1871048 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.4009. Min Act: -0.1700
Data Index: 3816310 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.3384. Min Act: -0.1700
Data Index: 2686977 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 1295956 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 4284763 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 3992908 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 4823734 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 1419514 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.3384. Min Act: -0.1700
Data Index: 5489779 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9009. Min Range: -8.9009
Max Act: 8.2759. Min Act: -0.1700
Data Index: 4371436 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19