Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1053. Min Range: -8.1053
Max Act: 8.1053. Min Act: -0.1700
Data Index: 5951197 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1053. Min Range: -8.1053
Max Act: 8.0428. Min Act: -0.1700
Data Index: 3150536 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.8866. Min Act: -0.1700
Data Index: 1681018 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.7928. Min Act: -0.1700
Data Index: 7975142 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.7928. Min Act: -0.1700
Data Index: 1263188 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.7303. Min Act: -0.1700
Data Index: 3871520 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.6678. Min Act: -0.1700
Data Index: 3979186 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.5741. Min Act: -0.1700
Data Index: 6047758 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.5116. Min Act: -0.1700
Data Index: 2248601 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.4803. Min Act: -0.1700
Data Index: 399502 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.4491. Min Act: -0.1700
Data Index: 6793107 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.4491. Min Act: -0.1700
Data Index: 1822160 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.3553. Min Act: -0.1700
Data Index: 3089946 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.3553. Min Act: -0.1700
Data Index: 2758036 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.3241. Min Act: -0.1700
Data Index: 1630197 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.2928. Min Act: -0.1700
Data Index: 613153 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.2928. Min Act: -0.1700
Data Index: 779213 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.2616. Min Act: -0.1700
Data Index: 6671837 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.2928. Min Act: -0.1700
Data Index: 1198418 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1053. Min Range: -8.1053
Max Act: 7.1991. Min Act: -0.1700
Data Index: 4244502 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19