Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 26.8987. Min Range: -26.8987
Max Act: 26.8987. Min Act: -0.1700
Data Index: 8468084 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 26.8987. Min Range: -26.8987
Max Act: 26.5237. Min Act: -0.1700
Data Index: 2516423 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 26.8987. Min Range: -26.8987
Max Act: 26.1487. Min Act: -0.1700
Data Index: 2185244 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.8987. Min Act: -0.1700
Data Index: 3540371 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.7737. Min Act: -0.1700
Data Index: 6837325 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.7737. Min Act: -0.1700
Data Index: 5100215 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.7737. Min Act: -0.1700
Data Index: 7684102 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.6487. Min Act: -0.1700
Data Index: 5168798 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.6487. Min Act: -0.1700
Data Index: 3417158 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.5237. Min Act: -0.1700
Data Index: 214772 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.5237. Min Act: -0.1700
Data Index: 62807 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.5237. Min Act: -0.1700
Data Index: 2483101 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.5237. Min Act: -0.1700
Data Index: 7415097 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.5237. Min Act: -0.1700
Data Index: 4443206 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 5041231 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 5004386 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 5385006 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 2700434 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 1542517 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 26.8987. Min Range: -26.8987
Max Act: 25.3987. Min Act: -0.1700
Data Index: 8586815 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19