Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1869 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9869. Min Act: -0.1700
Data Index: 4022147 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9557. Min Act: -0.1700
Data Index: 709056 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 5981352 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9557. Min Act: -0.1700
Data Index: 3354641 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6128714 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 2921792 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 1663166 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3139658 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4915290 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 308599 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4488080 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4075884 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 7607821 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 2904186 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 1401464 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 4872566 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 1719396 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6976212 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 448941 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 1957541 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19