Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7119. Min Range: -10.7119
Max Act: 10.7119. Min Act: -0.1700
Data Index: 6094151 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7119. Min Range: -10.7119
Max Act: 10.1494. Min Act: -0.1700
Data Index: 6138876 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7119. Min Range: -10.7119
Max Act: 10.0244. Min Act: -0.1700
Data Index: 271931 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.9619. Min Act: -0.1700
Data Index: 3301661 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.7744. Min Act: -0.1700
Data Index: 839833 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.7744. Min Act: -0.1700
Data Index: 3137281 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.7744. Min Act: -0.1700
Data Index: 7927725 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 3828587 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 115260 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 2290076 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 325963 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 6794284 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.6494. Min Act: -0.1700
Data Index: 3474878 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5244. Min Act: -0.1700
Data Index: 7887781 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5869. Min Act: -0.1700
Data Index: 7430722 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5869. Min Act: -0.1700
Data Index: 527883 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5869. Min Act: -0.1700
Data Index: 2776539 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5244. Min Act: -0.1700
Data Index: 7953852 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5244. Min Act: -0.1700
Data Index: 912852 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7119. Min Range: -10.7119
Max Act: 9.5244. Min Act: -0.1700
Data Index: 8173453 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19