Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1250. Min Range: -7.1250
Max Act: 7.1250. Min Act: -0.1700
Data Index: 7124249 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.9688. Min Act: -0.1700
Data Index: 6567896 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.7813. Min Act: -0.1700
Data Index: 1018012 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.7813. Min Act: -0.1700
Data Index: 4352077 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.7188. Min Act: -0.1700
Data Index: 942434 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.6563. Min Act: -0.1700
Data Index: 1341102 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.6563. Min Act: -0.1700
Data Index: 1395712 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.6250. Min Act: -0.1700
Data Index: 365105 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.5938. Min Act: -0.1700
Data Index: 1974599 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5935214 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4688. Min Act: -0.1700
Data Index: 2751843 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4688. Min Act: -0.1700
Data Index: 4141227 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5617286 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4063. Min Act: -0.1700
Data Index: 4598290 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4688. Min Act: -0.1700
Data Index: 560224 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4375. Min Act: -0.1700
Data Index: 5699534 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4375. Min Act: -0.1700
Data Index: 8608058 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4063. Min Act: -0.1700
Data Index: 4420995 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.4063. Min Act: -0.1700
Data Index: 226562 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1250. Min Range: -7.1250
Max Act: 6.3750. Min Act: -0.1700
Data Index: 5358557 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19