Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5341 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.6245. Min Act: -0.1700
Data Index: 6763626 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.3120. Min Act: -0.1700
Data Index: 1734563 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.1870. Min Act: -0.1700
Data Index: 6979845 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.1245. Min Act: -0.1700
Data Index: 3954857 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.1245. Min Act: -0.1700
Data Index: 5372774 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6245. Min Range: -8.6245
Max Act: 8.0620. Min Act: -0.1700
Data Index: 256586 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9683. Min Act: -0.1700
Data Index: 6484544 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9683. Min Act: -0.1700
Data Index: 4744142 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9683. Min Act: -0.1700
Data Index: 3244443 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9683. Min Act: -0.1700
Data Index: 2960557 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9370. Min Act: -0.1700
Data Index: 3288744 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9370. Min Act: -0.1700
Data Index: 7112658 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9370. Min Act: -0.1700
Data Index: 8044885 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9058. Min Act: -0.1700
Data Index: 7422741 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9058. Min Act: -0.1700
Data Index: 7587685 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.9058. Min Act: -0.1700
Data Index: 8011672 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.8433. Min Act: -0.1700
Data Index: 7065358 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.8433. Min Act: -0.1700
Data Index: 3444805 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.8433. Min Act: -0.1700
Data Index: 2064859 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6245. Min Range: -8.6245
Max Act: 7.8120. Min Act: -0.1700
Data Index: 7571614 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19