Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.5246. Min Act: -0.1700
Data Index: 5526957 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.3996. Min Act: -0.1700
Data Index: 4644466 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2746. Min Act: -0.1700
Data Index: 2526335 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2746. Min Act: -0.1700
Data Index: 6147422 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2746. Min Act: -0.1700
Data Index: 1487505 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2746. Min Act: -0.1700
Data Index: 3737313 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2121. Min Act: -0.1700
Data Index: 1780722 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.2121. Min Act: -0.1700
Data Index: 5459841 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.1496. Min Act: -0.1700
Data Index: 6904367 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.1496. Min Act: -0.1700
Data Index: 5971609 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.1496. Min Act: -0.1700
Data Index: 1974406 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0871. Min Act: -0.1700
Data Index: 2656152 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0871. Min Act: -0.1700
Data Index: 5363660 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0871. Min Act: -0.1700
Data Index: 2244373 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0871. Min Act: -0.1700
Data Index: 26582 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0871. Min Act: -0.1700
Data Index: 6944922 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0246. Min Act: -0.1700
Data Index: 6357713 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0246. Min Act: -0.1700
Data Index: 5088936 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0246. Min Act: -0.1700
Data Index: 6527387 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5246. Min Range: -8.5246
Max Act: 8.0246. Min Act: -0.1700
Data Index: 611951 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19