Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.8715. Min Act: -0.1700
Data Index: 6898880 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.8090. Min Act: -0.1700
Data Index: 910094 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.6840. Min Act: -0.1700
Data Index: 2463621 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.6215. Min Act: -0.1700
Data Index: 6705631 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.5590. Min Act: -0.1700
Data Index: 3357313 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.5590. Min Act: -0.1700
Data Index: 5774397 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.4965. Min Act: -0.1700
Data Index: 7946430 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.5590. Min Act: -0.1700
Data Index: 6503872 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.5590. Min Act: -0.1700
Data Index: 5514402 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.4340. Min Act: -0.1700
Data Index: 6451009 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.4340. Min Act: -0.1700
Data Index: 4647227 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.4340. Min Act: -0.1700
Data Index: 243926 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.3715. Min Act: -0.1700
Data Index: 4310102 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.3090. Min Act: -0.1700
Data Index: 5306238 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.3090. Min Act: -0.1700
Data Index: 5688698 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.3090. Min Act: -0.1700
Data Index: 8012760 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.2465. Min Act: -0.1700
Data Index: 138741 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.2465. Min Act: -0.1700
Data Index: 3565215 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.2465. Min Act: -0.1700
Data Index: 3608703 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8715. Min Range: -8.8715
Max Act: 8.2465. Min Act: -0.1700
Data Index: 3682352 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19