Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6991. Min Act: -0.1700
Data Index: 2011703 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6678. Min Act: -0.1700
Data Index: 6552173 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6365. Min Act: -0.1700
Data Index: 4697278 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6678. Min Act: -0.1700
Data Index: 1883629 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6678. Min Act: -0.1700
Data Index: 7037032 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6365. Min Act: -0.1700
Data Index: 216991 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6052. Min Act: -0.1700
Data Index: 5217328 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6678. Min Act: -0.1700
Data Index: 2011710 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6052. Min Act: -0.1700
Data Index: 6816237 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5113. Min Act: -0.1700
Data Index: 5361675 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5583. Min Act: -0.1700
Data Index: 6488896 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.6052. Min Act: -0.1700
Data Index: 64583 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5270. Min Act: -0.1700
Data Index: 5274313 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5426. Min Act: -0.1700
Data Index: 1288430 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5270. Min Act: -0.1700
Data Index: 2565845 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5583. Min Act: -0.1700
Data Index: 3342401 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5270. Min Act: -0.1700
Data Index: 1774162 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5113. Min Act: -0.1700
Data Index: 6133632 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5113. Min Act: -0.1700
Data Index: 6044424 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6991. Min Range: -3.6991
Max Act: 3.5113. Min Act: -0.1700
Data Index: 2296870 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19