Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 4472770 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 3672788 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1528. Min Act: -0.1700
Data Index: 5619214 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0903. Min Act: -0.1700
Data Index: 1329869 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 5230100 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 6806202 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 1156211 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0278. Min Act: -0.1700
Data Index: 1703412 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9965. Min Act: -0.1700
Data Index: 4472773 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9965. Min Act: -0.1700
Data Index: 1425598 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9653. Min Act: -0.1700
Data Index: 8180014 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 420428 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5855317 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 4332845 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 7824376 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 2859396 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 6408995 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 3687430 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1432295 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1648596 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19