Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.7232. Min Act: -0.1700
Data Index: 4183827 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.4107. Min Act: -0.1700
Data Index: 7189055 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.4107. Min Act: -0.1700
Data Index: 6766901 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.2857. Min Act: -0.1700
Data Index: 8747731 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.2232. Min Act: -0.1700
Data Index: 2772235 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0982. Min Act: -0.1700
Data Index: 1769815 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.1607. Min Act: -0.1700
Data Index: 5793729 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0670. Min Act: -0.1700
Data Index: 8198737 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0357. Min Act: -0.1700
Data Index: 1315408 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0045. Min Act: -0.1700
Data Index: 6935794 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0045. Min Act: -0.1700
Data Index: 1768902 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9732. Min Act: -0.1700
Data Index: 3787713 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7232. Min Range: -8.7232
Max Act: 8.0045. Min Act: -0.1700
Data Index: 6955493 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9732. Min Act: -0.1700
Data Index: 6802624 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9732. Min Act: -0.1700
Data Index: 3062833 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9420. Min Act: -0.1700
Data Index: 7846267 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9107. Min Act: -0.1700
Data Index: 1747558 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9420. Min Act: -0.1700
Data Index: 6932287 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.8795. Min Act: -0.1700
Data Index: 6649980 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7232. Min Range: -8.7232
Max Act: 7.9107. Min Act: -0.1700
Data Index: 5285640 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19