Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.9275. Min Act: -0.1700
Data Index: 7415207 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.9275. Min Act: -0.1700
Data Index: 6308072 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.9588. Min Act: -0.1700
Data Index: 7688060 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8650. Min Act: -0.1700
Data Index: 329160 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8963. Min Act: -0.1700
Data Index: 6956068 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 2990086 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8025. Min Act: -0.1700
Data Index: 8490769 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 899319 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8025. Min Act: -0.1700
Data Index: 4073805 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7713. Min Act: -0.1700
Data Index: 2562054 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8025. Min Act: -0.1700
Data Index: 2960778 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8025. Min Act: -0.1700
Data Index: 7322997 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7713. Min Act: -0.1700
Data Index: 87098 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7713. Min Act: -0.1700
Data Index: 5042201 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7400. Min Act: -0.1700
Data Index: 8665473 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.8025. Min Act: -0.1700
Data Index: 7026096 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7400. Min Act: -0.1700
Data Index: 1796311 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7713. Min Act: -0.1700
Data Index: 5391510 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7088. Min Act: -0.1700
Data Index: 5002440 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9588. Min Range: -5.9588
Max Act: 5.7088. Min Act: -0.1700
Data Index: 4409799 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19