Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2276 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.6641. Min Act: -0.1700
Data Index: 1878593 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.4766. Min Act: -0.1700
Data Index: 8525705 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.3204. Min Act: -0.1700
Data Index: 6590844 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2891. Min Act: -0.1700
Data Index: 7405848 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1041441 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2891. Min Act: -0.1700
Data Index: 3468330 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1329. Min Act: -0.1700
Data Index: 7802312 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1016. Min Act: -0.1700
Data Index: 8492407 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0704. Min Act: -0.1700
Data Index: 561369 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0391. Min Act: -0.1700
Data Index: 2403803 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0391. Min Act: -0.1700
Data Index: 5471180 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0391. Min Act: -0.1700
Data Index: 5914924 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0079. Min Act: -0.1700
Data Index: 7656015 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.0079. Min Act: -0.1700
Data Index: 7238131 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.8829. Min Act: -0.1700
Data Index: 102489 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.9141. Min Act: -0.1700
Data Index: 1633700 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.9141. Min Act: -0.1700
Data Index: 4234813 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.8516. Min Act: -0.1700
Data Index: 1717157 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.8516. Min Act: -0.1700
Data Index: 6980146 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6641. Min Range: -7.6641
Max Act: 6.8516. Min Act: -0.1700
Data Index: 5344464 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19