Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6133 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.6987. Min Act: -0.1700
Data Index: 6771842 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.3862. Min Act: -0.1700
Data Index: 378961 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6995648 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.3550. Min Act: -0.1700
Data Index: 6341634 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.3550. Min Act: -0.1700
Data Index: 4366349 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 7899092 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 4579738 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6002446 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 7480109 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2612. Min Act: -0.1700
Data Index: 499608 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2612. Min Act: -0.1700
Data Index: 5692834 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 8543886 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2300. Min Act: -0.1700
Data Index: 301095 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.2300. Min Act: -0.1700
Data Index: 5068390 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 7432181 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 7113340 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 3332206 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 835750 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 5344614 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6987. Min Range: -6.6987
Max Act: 6.1675. Min Act: -0.1700
Data Index: 4556056 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19