Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.5528. Min Act: -0.1700
Data Index: 639458 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.4903. Min Act: -0.1700
Data Index: 4746963 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.5528. Min Act: -0.1700
Data Index: 4793413 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.3028. Min Act: -0.1700
Data Index: 1651109 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.3653. Min Act: -0.1700
Data Index: 4121390 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.3028. Min Act: -0.1700
Data Index: 466268 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.3653. Min Act: -0.1700
Data Index: 3133543 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.1778. Min Act: -0.1700
Data Index: 2764234 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5528. Min Range: -14.5528
Max Act: 14.1153. Min Act: -0.1700
Data Index: 3894703 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.9278. Min Act: -0.1700
Data Index: 6291187 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.9903. Min Act: -0.1700
Data Index: 5858559 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.8653. Min Act: -0.1700
Data Index: 1044565 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.8653. Min Act: -0.1700
Data Index: 3555588 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.8028. Min Act: -0.1700
Data Index: 2730 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.8028. Min Act: -0.1700
Data Index: 7082885 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.7403. Min Act: -0.1700
Data Index: 8058620 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.7403. Min Act: -0.1700
Data Index: 4789854 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.7403. Min Act: -0.1700
Data Index: 2154070 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.6778. Min Act: -0.1700
Data Index: 6096789 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5528. Min Range: -14.5528
Max Act: 13.6778. Min Act: -0.1700
Data Index: 2259914 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19