Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4126 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0664. Min Range: -8.0664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 3084210 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.9414. Min Act: -0.1700
Data Index: 7884925 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.8789. Min Act: -0.1700
Data Index: 5444011 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.8164. Min Act: -0.1700
Data Index: 7426159 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.8164. Min Act: -0.1700
Data Index: 1849779 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.7539. Min Act: -0.1700
Data Index: 769639 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.6914. Min Act: -0.1700
Data Index: 7860787 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 4307251 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 3387160 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 758877 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 6816872 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5039. Min Act: -0.1700
Data Index: 4398438 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.4726. Min Act: -0.1700
Data Index: 6399920 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5468415 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5549111 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3476. Min Act: -0.1700
Data Index: 7469374 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3789. Min Act: -0.1700
Data Index: 7403740 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3164. Min Act: -0.1700
Data Index: 5283599 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3476. Min Act: -0.1700
Data Index: 5368070 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3789. Min Act: -0.1700
Data Index: 335322 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19