Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1249 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.1745. Min Act: -0.1700
Data Index: 1513648 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.2057. Min Act: -0.1700
Data Index: 2970685 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.1120. Min Act: -0.1700
Data Index: 6247517 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 8424864 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 6485317 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 5949846 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 3447644 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0182. Min Act: -0.1700
Data Index: 913045 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0182. Min Act: -0.1700
Data Index: 8019818 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9870. Min Act: -0.1700
Data Index: 6391401 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9870. Min Act: -0.1700
Data Index: 7407714 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9870. Min Act: -0.1700
Data Index: 7351800 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0182. Min Act: -0.1700
Data Index: 6592297 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9870. Min Act: -0.1700
Data Index: 2187222 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9870. Min Act: -0.1700
Data Index: 4230357 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9557. Min Act: -0.1700
Data Index: 423060 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9245. Min Act: -0.1700
Data Index: 7961470 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9557. Min Act: -0.1700
Data Index: 3301497 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9245. Min Act: -0.1700
Data Index: 2359358 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9245. Min Act: -0.1700
Data Index: 7737093 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19