Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5587 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.9824. Min Act: -0.1700
Data Index: 2678684 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.9199. Min Act: -0.1700
Data Index: 5300091 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.8887. Min Act: -0.1700
Data Index: 5300092 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.8262. Min Act: -0.1700
Data Index: 8180347 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.8262. Min Act: -0.1700
Data Index: 4782713 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7316332 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7275784 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8346037 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6843042 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3725082 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7012. Min Act: -0.1700
Data Index: 5986213 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7012. Min Act: -0.1700
Data Index: 7463043 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.7012. Min Act: -0.1700
Data Index: 4782714 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6699. Min Act: -0.1700
Data Index: 2877452 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6699. Min Act: -0.1700
Data Index: 178691 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6699. Min Act: -0.1700
Data Index: 2025492 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6699. Min Act: -0.1700
Data Index: 8140013 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6387. Min Act: -0.1700
Data Index: 6828162 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6387. Min Act: -0.1700
Data Index: 7249471 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9824. Min Range: -5.9824
Max Act: 5.6699. Min Act: -0.1700
Data Index: 2588891 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19