Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3099. Min Range: -8.3099
Max Act: 8.3099. Min Act: -0.1700
Data Index: 5761650 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3099. Min Range: -8.3099
Max Act: 8.2474. Min Act: -0.1700
Data Index: 422372 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3099. Min Range: -8.3099
Max Act: 8.0599. Min Act: -0.1700
Data Index: 2559877 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3099. Min Range: -8.3099
Max Act: 8.1224. Min Act: -0.1700
Data Index: 5094164 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9349. Min Act: -0.1700
Data Index: 1627918 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3099. Min Range: -8.3099
Max Act: 8.0599. Min Act: -0.1700
Data Index: 1234119 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9974. Min Act: -0.1700
Data Index: 3270229 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9974. Min Act: -0.1700
Data Index: 628682 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9974. Min Act: -0.1700
Data Index: 1847891 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9349. Min Act: -0.1700
Data Index: 45711 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9349. Min Act: -0.1700
Data Index: 1703426 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.9349. Min Act: -0.1700
Data Index: 8095947 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 4839332 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 6490233 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 4946504 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 976173 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 7917619 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8724. Min Act: -0.1700
Data Index: 1295062 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8099. Min Act: -0.1700
Data Index: 5038838 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3099. Min Range: -8.3099
Max Act: 7.8099. Min Act: -0.1700
Data Index: 5413652 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19