Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.8891. Min Act: -0.1700
Data Index: 3855941 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7953. Min Act: -0.1700
Data Index: 944083 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7641. Min Act: -0.1700
Data Index: 5943228 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7641. Min Act: -0.1700
Data Index: 7861329 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7328. Min Act: -0.1700
Data Index: 8740959 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7016. Min Act: -0.1700
Data Index: 1128098 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4061199 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6703. Min Act: -0.1700
Data Index: 7410179 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6703. Min Act: -0.1700
Data Index: 1964696 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6391. Min Act: -0.1700
Data Index: 973576 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6391. Min Act: -0.1700
Data Index: 2796345 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4053079 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6703. Min Act: -0.1700
Data Index: 4019082 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6078. Min Act: -0.1700
Data Index: 3000820 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6078. Min Act: -0.1700
Data Index: 70486 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6078. Min Act: -0.1700
Data Index: 5025948 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6078. Min Act: -0.1700
Data Index: 8354764 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.6078. Min Act: -0.1700
Data Index: 3231859 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.5453. Min Act: -0.1700
Data Index: 7116129 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8891. Min Range: -5.8891
Max Act: 5.5453. Min Act: -0.1700
Data Index: 6436859 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19