Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.4805. Min Act: -0.1700
Data Index: 7579695 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.4805. Min Act: -0.1700
Data Index: 6368723 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.4180. Min Act: -0.1700
Data Index: 2996703 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.2930. Min Act: -0.1700
Data Index: 3591117 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.2305. Min Act: -0.1700
Data Index: 4096320 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.2305. Min Act: -0.1700
Data Index: 2882172 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.2305. Min Act: -0.1700
Data Index: 4075341 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1680. Min Act: -0.1700
Data Index: 5012454 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1055. Min Act: -0.1700
Data Index: 3119982 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1680. Min Act: -0.1700
Data Index: 7574851 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1055. Min Act: -0.1700
Data Index: 2228745 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1055. Min Act: -0.1700
Data Index: 2599393 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.1055. Min Act: -0.1700
Data Index: 2446047 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.0430. Min Act: -0.1700
Data Index: 2712859 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4805. Min Range: -8.4805
Max Act: 7.9805. Min Act: -0.1700
Data Index: 1496525 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4805. Min Range: -8.4805
Max Act: 7.9180. Min Act: -0.1700
Data Index: 2803019 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4805. Min Range: -8.4805
Max Act: 7.9805. Min Act: -0.1700
Data Index: 1960173 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4805. Min Range: -8.4805
Max Act: 8.0430. Min Act: -0.1700
Data Index: 5651432 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4805. Min Range: -8.4805
Max Act: 7.9805. Min Act: -0.1700
Data Index: 4037918 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4805. Min Range: -8.4805
Max Act: 7.9180. Min Act: -0.1700
Data Index: 339295 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19