Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0955. Min Act: -0.1700
Data Index: 6611119 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0017. Min Act: -0.1700
Data Index: 2445948 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4754453 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4359214 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0017. Min Act: -0.1700
Data Index: 1254258 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.9392. Min Act: -0.1700
Data Index: 5479345 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.9080. Min Act: -0.1700
Data Index: 844624 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4097627 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8455. Min Act: -0.1700
Data Index: 6452784 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8142. Min Act: -0.1700
Data Index: 5859407 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8142. Min Act: -0.1700
Data Index: 4097619 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8142. Min Act: -0.1700
Data Index: 7104699 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8142. Min Act: -0.1700
Data Index: 4105782 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8142. Min Act: -0.1700
Data Index: 1115314 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 2939700 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 3122275 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 6452779 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 355806 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 4105784 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7517. Min Act: -0.1700
Data Index: 3130868 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19