Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1324582 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0009. Min Range: -5.0009
Max Act: 5.0009. Min Act: -0.1700
Data Index: 2759700 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 8181588 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.8446. Min Act: -0.1700
Data Index: 7854318 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 7241078 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.8134. Min Act: -0.1700
Data Index: 2821469 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.8134. Min Act: -0.1700
Data Index: 223866 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.7508. Min Act: -0.1700
Data Index: 7387145 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.7508. Min Act: -0.1700
Data Index: 1093727 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.7196. Min Act: -0.1700
Data Index: 1421817 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6883. Min Act: -0.1700
Data Index: 4875673 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6883. Min Act: -0.1700
Data Index: 5180524 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6571. Min Act: -0.1700
Data Index: 5362517 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6571. Min Act: -0.1700
Data Index: 4157471 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6571. Min Act: -0.1700
Data Index: 3771788 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6571. Min Act: -0.1700
Data Index: 8587439 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6571. Min Act: -0.1700
Data Index: 7455097 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6258. Min Act: -0.1700
Data Index: 1225754 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6258. Min Act: -0.1700
Data Index: 4749303 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0009. Min Range: -5.0009
Max Act: 4.6258. Min Act: -0.1700
Data Index: 673581 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19