Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0787. Min Range: -8.0787
Max Act: 8.0787. Min Act: -0.1700
Data Index: 765441 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.6412. Min Act: -0.1700
Data Index: 609836 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.6412. Min Act: -0.1700
Data Index: 4860773 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.6412. Min Act: -0.1700
Data Index: 3246901 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.6412. Min Act: -0.1700
Data Index: 5795927 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.5475. Min Act: -0.1700
Data Index: 6331723 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.5475. Min Act: -0.1700
Data Index: 8718444 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.5162. Min Act: -0.1700
Data Index: 2004650 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.4537. Min Act: -0.1700
Data Index: 1870785 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.4850. Min Act: -0.1700
Data Index: 4454105 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.3600. Min Act: -0.1700
Data Index: 1083237 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.3600. Min Act: -0.1700
Data Index: 6747131 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.3600. Min Act: -0.1700
Data Index: 2801154 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 7860097 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2975. Min Act: -0.1700
Data Index: 6528579 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2350. Min Act: -0.1700
Data Index: 1403858 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.3287. Min Act: -0.1700
Data Index: 3197884 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 2037278 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 982383 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0787. Min Range: -8.0787
Max Act: 7.2037. Min Act: -0.1700
Data Index: 3340012 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19