Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0698. Min Range: -7.0698
Max Act: 7.0698. Min Act: -0.1700
Data Index: 614245 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5698. Min Act: -0.1700
Data Index: 1737107 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5385. Min Act: -0.1700
Data Index: 1605752 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5073. Min Act: -0.1700
Data Index: 724433 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4760. Min Act: -0.1700
Data Index: 827956 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4448. Min Act: -0.1700
Data Index: 744129 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4135. Min Act: -0.1700
Data Index: 1381235 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3823. Min Act: -0.1700
Data Index: 3727646 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 816559 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7198709 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2885. Min Act: -0.1700
Data Index: 1339558 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2885. Min Act: -0.1700
Data Index: 7167560 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8492367 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2573. Min Act: -0.1700
Data Index: 7102139 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2573. Min Act: -0.1700
Data Index: 1255371 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2260. Min Act: -0.1700
Data Index: 7885523 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2260. Min Act: -0.1700
Data Index: 4304871 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2260. Min Act: -0.1700
Data Index: 8779845 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.2260. Min Act: -0.1700
Data Index: 2708611 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4761640 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19