Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0050. Min Range: -8.0050
Max Act: 8.0050. Min Act: -0.1700
Data Index: 1125473 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0050. Min Range: -8.0050
Max Act: 8.0050. Min Act: -0.1700
Data Index: 7142945 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0050. Min Range: -8.0050
Max Act: 8.0050. Min Act: -0.1700
Data Index: 6607194 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8800. Min Act: -0.1700
Data Index: 4465928 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8800. Min Act: -0.1700
Data Index: 1473256 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8800. Min Act: -0.1700
Data Index: 1040245 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8175. Min Act: -0.1700
Data Index: 3626657 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8175. Min Act: -0.1700
Data Index: 295622 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.8175. Min Act: -0.1700
Data Index: 1193182 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.7550. Min Act: -0.1700
Data Index: 1008829 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.7550. Min Act: -0.1700
Data Index: 5074663 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.7550. Min Act: -0.1700
Data Index: 2347252 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.7550. Min Act: -0.1700
Data Index: 6115169 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.7550. Min Act: -0.1700
Data Index: 557466 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6925. Min Act: -0.1700
Data Index: 6936783 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6925. Min Act: -0.1700
Data Index: 1223417 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6925. Min Act: -0.1700
Data Index: 3256686 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6925. Min Act: -0.1700
Data Index: 1984653 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6300. Min Act: -0.1700
Data Index: 278901 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0050. Min Range: -8.0050
Max Act: 7.6300. Min Act: -0.1700
Data Index: 1363239 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19