Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5970. Min Range: -9.5970
Max Act: 9.5970. Min Act: -0.1700
Data Index: 7552208 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5970. Min Range: -9.5970
Max Act: 9.2220. Min Act: -0.1700
Data Index: 6742001 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5970. Min Range: -9.5970
Max Act: 9.1595. Min Act: -0.1700
Data Index: 992231 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.9095. Min Act: -0.1700
Data Index: 791480 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.9095. Min Act: -0.1700
Data Index: 2854958 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.8470. Min Act: -0.1700
Data Index: 6713546 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7845. Min Act: -0.1700
Data Index: 7722652 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7845. Min Act: -0.1700
Data Index: 4133452 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7845. Min Act: -0.1700
Data Index: 5239994 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7220. Min Act: -0.1700
Data Index: 8197666 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7220. Min Act: -0.1700
Data Index: 3574256 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.7220. Min Act: -0.1700
Data Index: 1229794 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 2993660 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 2704708 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 179865 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.5970. Min Act: -0.1700
Data Index: 642059 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 194334 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 8012009 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 5832295 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5970. Min Range: -9.5970
Max Act: 8.6595. Min Act: -0.1700
Data Index: 2032992 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19