Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.9617. Min Act: -0.1700
Data Index: 3266950 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.8055. Min Act: -0.1700
Data Index: 694530 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5514024 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.7430. Min Act: -0.1700
Data Index: 783118 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.7430. Min Act: -0.1700
Data Index: 3207907 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.6805. Min Act: -0.1700
Data Index: 6987386 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7229072 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7113283 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.6805. Min Act: -0.1700
Data Index: 4901328 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.6492. Min Act: -0.1700
Data Index: 6153747 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.6492. Min Act: -0.1700
Data Index: 6184037 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8176477 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5867. Min Act: -0.1700
Data Index: 3668798 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5739242 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5867. Min Act: -0.1700
Data Index: 6066002 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5555. Min Act: -0.1700
Data Index: 2103961 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5555. Min Act: -0.1700
Data Index: 6222597 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5555. Min Act: -0.1700
Data Index: 2225030 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5555. Min Act: -0.1700
Data Index: 4295132 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9617. Min Range: -5.9617
Max Act: 5.5555. Min Act: -0.1700
Data Index: 772780 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19