Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1843 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2904. Min Act: -0.1700
Data Index: 1226061 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2747. Min Act: -0.1700
Data Index: 2031043 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2747. Min Act: -0.1700
Data Index: 13598 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2433. Min Act: -0.1700
Data Index: 557372 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2433. Min Act: -0.1700
Data Index: 5790962 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 8587398 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2119. Min Act: -0.1700
Data Index: 2131659 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 824591 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1962. Min Act: -0.1700
Data Index: 4099820 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2119. Min Act: -0.1700
Data Index: 5680638 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2119. Min Act: -0.1700
Data Index: 2353648 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 1743823 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2119. Min Act: -0.1700
Data Index: 7749976 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 8257562 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 830012 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2119. Min Act: -0.1700
Data Index: 7774959 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1962. Min Act: -0.1700
Data Index: 254303 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1962. Min Act: -0.1700
Data Index: 7540600 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1962. Min Act: -0.1700
Data Index: 372531 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 6133087 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19