Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0197. Min Range: -6.0197
Max Act: 6.0197. Min Act: -0.1700
Data Index: 4909308 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.9885. Min Act: -0.1700
Data Index: 5601098 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.8635. Min Act: -0.1700
Data Index: 6454729 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.8635. Min Act: -0.1700
Data Index: 5202952 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.7697. Min Act: -0.1700
Data Index: 7876074 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.8010. Min Act: -0.1700
Data Index: 5299337 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6760. Min Act: -0.1700
Data Index: 3865635 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.7072. Min Act: -0.1700
Data Index: 4662685 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.7072. Min Act: -0.1700
Data Index: 1218373 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5427421 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6760. Min Act: -0.1700
Data Index: 4711479 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 3929293 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7756597 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 1601098 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 5814270 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 1532437 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 5853988 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6135. Min Act: -0.1700
Data Index: 4567780 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6135. Min Act: -0.1700
Data Index: 1745093 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0197. Min Range: -6.0197
Max Act: 5.6447. Min Act: -0.1700
Data Index: 5799655 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19