Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7812. Min Range: -8.7812
Max Act: 8.7812. Min Act: -0.1700
Data Index: 1528553 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7812. Min Range: -8.7812
Max Act: 8.0625. Min Act: -0.1700
Data Index: 2818468 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.9375. Min Act: -0.1700
Data Index: 6390767 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.8750. Min Act: -0.1700
Data Index: 394053 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.8125. Min Act: -0.1700
Data Index: 6351424 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.6562. Min Act: -0.1700
Data Index: 3889092 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.6250. Min Act: -0.1700
Data Index: 3283920 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.6250. Min Act: -0.1700
Data Index: 4432742 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5937. Min Act: -0.1700
Data Index: 6486057 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 7340688 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 3324727 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 5932469 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5625. Min Act: -0.1700
Data Index: 3881059 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.5312. Min Act: -0.1700
Data Index: 8359423 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.4375. Min Act: -0.1700
Data Index: 8257969 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.4375. Min Act: -0.1700
Data Index: 6035204 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.4687. Min Act: -0.1700
Data Index: 2427345 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.4687. Min Act: -0.1700
Data Index: 6009136 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.4375. Min Act: -0.1700
Data Index: 7273577 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7812. Min Range: -8.7812
Max Act: 7.3750. Min Act: -0.1700
Data Index: 1102877 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19