Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5509 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0188. Min Range: -10.0188
Max Act: 10.0188. Min Act: -0.1700
Data Index: 8495235 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.9563. Min Act: -0.1700
Data Index: 8495232 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.6438. Min Act: -0.1700
Data Index: 4354020 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.5188. Min Act: -0.1700
Data Index: 8279274 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.4563. Min Act: -0.1700
Data Index: 2778938 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.3313. Min Act: -0.1700
Data Index: 670528 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.3313. Min Act: -0.1700
Data Index: 6498107 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.3938. Min Act: -0.1700
Data Index: 3997691 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2688. Min Act: -0.1700
Data Index: 4471004 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2688. Min Act: -0.1700
Data Index: 4810818 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2688. Min Act: -0.1700
Data Index: 8495236 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2063. Min Act: -0.1700
Data Index: 34666 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2063. Min Act: -0.1700
Data Index: 4197086 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2063. Min Act: -0.1700
Data Index: 5868038 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2063. Min Act: -0.1700
Data Index: 6285238 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.2063. Min Act: -0.1700
Data Index: 8495230 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.1438. Min Act: -0.1700
Data Index: 8494540 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.1438. Min Act: -0.1700
Data Index: 6156498 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.0813. Min Act: -0.1700
Data Index: 7508721 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0188. Min Range: -10.0188
Max Act: 9.0813. Min Act: -0.1700
Data Index: 8495227 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19