Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 1389319 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.7469. Min Act: -0.1700
Data Index: 554254 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6844. Min Act: -0.1700
Data Index: 1279312 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.7156. Min Act: -0.1700
Data Index: 5215995 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 3464338 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 119691 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 3173134 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 5564101 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 2957611 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 6705855 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 2145244 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 5364054 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 3699590 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 2639440 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 119703 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 2467747 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 1690781 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 6198814 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5281. Min Act: -0.1700
Data Index: 3135457 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 186184 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19