Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6099. Min Range: -9.6099
Max Act: 9.6099. Min Act: -0.1700
Data Index: 3341441 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.9849. Min Act: -0.1700
Data Index: 2813357 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.9224. Min Act: -0.1699
Data Index: 8620504 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.8599. Min Act: -0.1700
Data Index: 3412726 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.7974. Min Act: -0.1700
Data Index: 2666234 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.6724. Min Act: -0.1700
Data Index: 569559 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.6099. Min Act: -0.1700
Data Index: 2563913 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.6099. Min Act: -0.1700
Data Index: 5187899 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.5474. Min Act: -0.1700
Data Index: 5803299 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.5474. Min Act: -0.1700
Data Index: 4101490 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.6099. Min Act: -0.1700
Data Index: 6170599 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4849. Min Act: -0.1700
Data Index: 7654022 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4849. Min Act: -0.1700
Data Index: 4800915 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.3599. Min Act: -0.1700
Data Index: 3684826 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4224. Min Act: -0.1700
Data Index: 3341440 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4849. Min Act: -0.1700
Data Index: 3645710 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4849. Min Act: -0.1700
Data Index: 2456557 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4224. Min Act: -0.1700
Data Index: 207096 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4224. Min Act: -0.1700
Data Index: 5244217 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6099. Min Range: -9.6099
Max Act: 8.4849. Min Act: -0.1700
Data Index: 5330397 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19