Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.7867. Min Act: -0.1700
Data Index: 6432266 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 1598345 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 2073169 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 851239 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 7824835 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 7766478 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.6617. Min Act: -0.1700
Data Index: 2891211 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.5992. Min Act: -0.1700
Data Index: 7702781 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.5992. Min Act: -0.1700
Data Index: 19960 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.5367. Min Act: -0.1700
Data Index: 1971270 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.5367. Min Act: -0.1700
Data Index: 3475044 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.5367. Min Act: -0.1700
Data Index: 8751169 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 2261662 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 7508998 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4117. Min Act: -0.1700
Data Index: 1469137 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 610804 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 3628467 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 19975 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 6283582 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7867. Min Range: -9.7867
Max Act: 9.4742. Min Act: -0.1700
Data Index: 5845401 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19