Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4418 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.6944. Min Act: -0.1700
Data Index: 2561056 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.2882. Min Act: -0.1700
Data Index: 4758585 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.2569. Min Act: -0.1700
Data Index: 8109490 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1632. Min Act: -0.1700
Data Index: 6067687 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1944. Min Act: -0.1700
Data Index: 6527601 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1632. Min Act: -0.1700
Data Index: 6498399 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1632. Min Act: -0.1700
Data Index: 2358601 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1632. Min Act: -0.1700
Data Index: 2898781 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 5020817 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 677589 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 2334972 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 275036 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0694. Min Act: -0.1700
Data Index: 36841 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0694. Min Act: -0.1700
Data Index: 3820683 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0694. Min Act: -0.1700
Data Index: 5905094 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0694. Min Act: -0.1700
Data Index: 6173626 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0694. Min Act: -0.1700
Data Index: 7497642 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0382. Min Act: -0.1700
Data Index: 7217476 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0382. Min Act: -0.1700
Data Index: 1815582 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6944. Min Range: -7.6944
Max Act: 7.0069. Min Act: -0.1700
Data Index: 3315974 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19