Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.9875. Min Act: -0.1700
Data Index: 6426522 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.8625. Min Act: -0.1700
Data Index: 1544764 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.8000. Min Act: -0.1700
Data Index: 5786067 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.8000. Min Act: -0.1700
Data Index: 3296934 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.7375. Min Act: -0.1700
Data Index: 4399057 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.7062. Min Act: -0.1700
Data Index: 8272117 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.7062. Min Act: -0.1700
Data Index: 5492566 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.7062. Min Act: -0.1700
Data Index: 8593176 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6750. Min Act: -0.1700
Data Index: 234773 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6750. Min Act: -0.1700
Data Index: 5926733 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6750. Min Act: -0.1700
Data Index: 1719073 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6437. Min Act: -0.1700
Data Index: 8618688 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7859797 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6437. Min Act: -0.1700
Data Index: 1537897 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2683162 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6125. Min Act: -0.1700
Data Index: 5210710 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6125. Min Act: -0.1700
Data Index: 1065529 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.6437. Min Act: -0.1700
Data Index: 3860748 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.5500. Min Act: -0.1700
Data Index: 1378886 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9875. Min Range: -6.9875
Max Act: 6.5812. Min Act: -0.1700
Data Index: 3112510 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19