Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5260 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0217. Min Range: -7.0217
Max Act: 7.0217. Min Act: -0.1700
Data Index: 6571773 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.8967. Min Act: -0.1700
Data Index: 7788021 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.8342. Min Act: -0.1700
Data Index: 6595427 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7717. Min Act: -0.1700
Data Index: 1381636 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.8342. Min Act: -0.1700
Data Index: 2591979 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7717. Min Act: -0.1700
Data Index: 3542741 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7717. Min Act: -0.1700
Data Index: 3792523 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7717. Min Act: -0.1700
Data Index: 4142182 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7717. Min Act: -0.1700
Data Index: 5604410 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 3179994 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 1186749 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 5619431 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 8174162 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 6658348 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.6779. Min Act: -0.1700
Data Index: 2703735 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.7092. Min Act: -0.1700
Data Index: 7957534 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.6779. Min Act: -0.1700
Data Index: 1422166 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.6779. Min Act: -0.1700
Data Index: 8331712 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.6779. Min Act: -0.1700
Data Index: 6021639 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0217. Min Range: -7.0217
Max Act: 6.6779. Min Act: -0.1700
Data Index: 5008039 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19