Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.2628. Min Act: -0.1700
Data Index: 3786071 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.1466. Min Act: -0.1700
Data Index: 1476716 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.1132. Min Act: -0.1700
Data Index: 5046562 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0630. Min Act: -0.1700
Data Index: 4369079 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0797. Min Act: -0.1700
Data Index: 6174525 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0797. Min Act: -0.1700
Data Index: 7545515 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0797. Min Act: -0.1700
Data Index: 5130733 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0797. Min Act: -0.1700
Data Index: 7432631 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0630. Min Act: -0.1700
Data Index: 7391430 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0630. Min Act: -0.1700
Data Index: 4018085 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0797. Min Act: -0.1700
Data Index: 2325821 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0630. Min Act: -0.1700
Data Index: 462503 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0293. Min Act: -0.1700
Data Index: 3004842 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0293. Min Act: -0.1700
Data Index: 963798 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0461. Min Act: -0.1700
Data Index: 1006987 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2628. Min Range: -2.2628
Max Act: 2.0124. Min Act: -0.1700
Data Index: 5581885 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2628. Min Range: -2.2628
Max Act: 1.9955. Min Act: -0.1700
Data Index: 4303076 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2628. Min Range: -2.2628
Max Act: 1.9955. Min Act: -0.1700
Data Index: 92863 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2628. Min Range: -2.2628
Max Act: 1.9955. Min Act: -0.1700
Data Index: 2664278 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2628. Min Range: -2.2628
Max Act: 1.9955. Min Act: -0.1700
Data Index: 390439 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19