Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.7875. Min Act: -0.1700
Data Index: 1433043 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.1313. Min Act: -0.1700
Data Index: 1707710 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.1313. Min Act: -0.1700
Data Index: 1390942 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.0688. Min Act: -0.1700
Data Index: 8282718 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.0375. Min Act: -0.1700
Data Index: 4225565 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.0688. Min Act: -0.1700
Data Index: 1211588 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7875. Min Range: -6.7875
Max Act: 6.0375. Min Act: -0.1700
Data Index: 5254156 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.9750. Min Act: -0.1700
Data Index: 4487357 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.9438. Min Act: -0.1700
Data Index: 6332446 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.9125. Min Act: -0.1700
Data Index: 7911926 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.9125. Min Act: -0.1700
Data Index: 7410056 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8813. Min Act: -0.1700
Data Index: 1694650 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8500. Min Act: -0.1700
Data Index: 6995441 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8188. Min Act: -0.1700
Data Index: 240042 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8500. Min Act: -0.1700
Data Index: 4171199 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8188. Min Act: -0.1700
Data Index: 5168564 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8500. Min Act: -0.1700
Data Index: 1397593 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8188. Min Act: -0.1700
Data Index: 5733521 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8188. Min Act: -0.1700
Data Index: 2886798 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7875. Min Range: -6.7875
Max Act: 5.8188. Min Act: -0.1700
Data Index: 3754813 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19