Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.9517. Min Act: -0.1700
Data Index: 7082711 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.9517. Min Act: -0.1700
Data Index: 786323 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.7955. Min Act: -0.1700
Data Index: 4614580 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.7642. Min Act: -0.1700
Data Index: 5267451 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.7330. Min Act: -0.1700
Data Index: 4359913 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6705. Min Act: -0.1700
Data Index: 4819915 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6705. Min Act: -0.1700
Data Index: 4284610 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6705. Min Act: -0.1700
Data Index: 6103834 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6705. Min Act: -0.1700
Data Index: 8330542 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5970503 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6392. Min Act: -0.1700
Data Index: 2140097 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5249582 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 3020614 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 4403859 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 2295440 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 749652 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.6080. Min Act: -0.1700
Data Index: 8142045 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.5455. Min Act: -0.1700
Data Index: 2899619 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.5767. Min Act: -0.1700
Data Index: 3959898 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9517. Min Range: -5.9517
Max Act: 5.5767. Min Act: -0.1700
Data Index: 7115600 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19