Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1876. Min Range: -15.1876
Max Act: 15.1876. Min Act: -0.1700
Data Index: 2165517 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.6251. Min Act: -0.1700
Data Index: 8804651 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.5626. Min Act: -0.1700
Data Index: 2926966 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.4376. Min Act: -0.1700
Data Index: 4383934 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.3751. Min Act: -0.1700
Data Index: 3883569 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.1251. Min Act: -0.1700
Data Index: 1791737 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.0626. Min Act: -0.1700
Data Index: 8496461 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.0626. Min Act: -0.1700
Data Index: 2459767 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.0626. Min Act: -0.1700
Data Index: 7643195 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.0626. Min Act: -0.1700
Data Index: 522391 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1876. Min Range: -15.1876
Max Act: 14.0001. Min Act: -0.1700
Data Index: 3640976 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.9376. Min Act: -0.1700
Data Index: 4059717 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.8751. Min Act: -0.1700
Data Index: 3087130 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.8751. Min Act: -0.1700
Data Index: 2938046 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.8751. Min Act: -0.1700
Data Index: 6171085 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.8751. Min Act: -0.1700
Data Index: 8727364 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.7501. Min Act: -0.1700
Data Index: 2798317 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.7501. Min Act: -0.1700
Data Index: 5708670 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.6876. Min Act: -0.1700
Data Index: 6657760 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1876. Min Range: -15.1876
Max Act: 13.6251. Min Act: -0.1700
Data Index: 4105890 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19