Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.9014. Min Act: -0.1700
Data Index: 6241087 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.8077. Min Act: -0.1700
Data Index: 7264285 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.8077. Min Act: -0.1700
Data Index: 8751867 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.7764. Min Act: -0.1700
Data Index: 5806360 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.7764. Min Act: -0.1700
Data Index: 5068724 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.7764. Min Act: -0.1700
Data Index: 1346946 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6827. Min Act: -0.1700
Data Index: 7853641 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.7139. Min Act: -0.1700
Data Index: 2831407 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6827. Min Act: -0.1700
Data Index: 2768825 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6827. Min Act: -0.1700
Data Index: 8259701 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6514. Min Act: -0.1700
Data Index: 1452503 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6202. Min Act: -0.1700
Data Index: 3813120 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6514. Min Act: -0.1700
Data Index: 3580128 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6514. Min Act: -0.1700
Data Index: 993618 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4177130 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6047323 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6012104 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.6202. Min Act: -0.1700
Data Index: 66041 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.5889. Min Act: -0.1700
Data Index: 7004375 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9014. Min Range: -5.9014
Max Act: 5.5889. Min Act: -0.1700
Data Index: 5348528 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19