Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.5867. Min Range: -14.5867
Max Act: 14.5867. Min Act: -0.1700
Data Index: 1495853 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5867. Min Range: -14.5867
Max Act: 14.3992. Min Act: -0.1700
Data Index: 5685922 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5867. Min Range: -14.5867
Max Act: 14.1492. Min Act: -0.1700
Data Index: 5958568 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5867. Min Range: -14.5867
Max Act: 14.1492. Min Act: -0.1700
Data Index: 5345 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5867. Min Range: -14.5867
Max Act: 14.1492. Min Act: -0.1700
Data Index: 7192253 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.9617. Min Act: -0.1700
Data Index: 2919808 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.9617. Min Act: -0.1700
Data Index: 4852518 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.7742. Min Act: -0.1700
Data Index: 4673197 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.6492. Min Act: -0.1700
Data Index: 6887213 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.6492. Min Act: -0.1700
Data Index: 4825383 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.7117. Min Act: -0.1700
Data Index: 6778757 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.6492. Min Act: -0.1700
Data Index: 8748208 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.4617. Min Act: -0.1700
Data Index: 133873 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.3992. Min Act: -0.1700
Data Index: 8803691 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.4617. Min Act: -0.1700
Data Index: 2771053 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.4617. Min Act: -0.1700
Data Index: 4795170 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.3992. Min Act: -0.1700
Data Index: 4527400 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.3992. Min Act: -0.1700
Data Index: 6455815 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.3367. Min Act: -0.1700
Data Index: 2635984 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5867. Min Range: -14.5867
Max Act: 13.2742. Min Act: -0.1700
Data Index: 126891 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19