Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1558. Min Range: -6.1558
Max Act: 6.1558. Min Act: -0.1700
Data Index: 4852635 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.8746. Min Act: -0.1700
Data Index: 5692632 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1925865 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.8433. Min Act: -0.1700
Data Index: 3554449 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.7808. Min Act: -0.1700
Data Index: 2051400 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.7183. Min Act: -0.1700
Data Index: 669867 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.7183. Min Act: -0.1700
Data Index: 7911433 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.7183. Min Act: -0.1700
Data Index: 8161977 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6558. Min Act: -0.1700
Data Index: 5007607 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6438407 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4160467 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6246. Min Act: -0.1700
Data Index: 3375751 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6246. Min Act: -0.1700
Data Index: 1704111 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6246. Min Act: -0.1700
Data Index: 4195605 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6246. Min Act: -0.1700
Data Index: 2631534 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.6246. Min Act: -0.1700
Data Index: 2934914 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.5933. Min Act: -0.1700
Data Index: 2652560 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.5933. Min Act: -0.1700
Data Index: 3958344 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.5933. Min Act: -0.1700
Data Index: 6936093 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1558. Min Range: -6.1558
Max Act: 5.5933. Min Act: -0.1700
Data Index: 4278065 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19