Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5590 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1812. Min Range: -8.1812
Max Act: 8.1812. Min Act: -0.1700
Data Index: 2487417 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1812. Min Range: -8.1812
Max Act: 8.0874. Min Act: -0.1700
Data Index: 1677125 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.9312. Min Act: -0.1700
Data Index: 5330234 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.9312. Min Act: -0.1700
Data Index: 4326949 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.8374. Min Act: -0.1700
Data Index: 5103698 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.8687. Min Act: -0.1700
Data Index: 912314 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.8999. Min Act: -0.1700
Data Index: 8829663 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7749. Min Act: -0.1700
Data Index: 6124376 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.8062. Min Act: -0.1700
Data Index: 2318708 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.8062. Min Act: -0.1700
Data Index: 7040404 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7749. Min Act: -0.1700
Data Index: 2097343 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7437. Min Act: -0.1700
Data Index: 8557928 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7124. Min Act: -0.1700
Data Index: 6589497 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7124. Min Act: -0.1700
Data Index: 7031853 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.7124. Min Act: -0.1700
Data Index: 2900283 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.6812. Min Act: -0.1700
Data Index: 3564154 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.6812. Min Act: -0.1700
Data Index: 4947714 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.6812. Min Act: -0.1700
Data Index: 3856237 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.6499. Min Act: -0.1700
Data Index: 6297771 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1812. Min Range: -8.1812
Max Act: 7.6499. Min Act: -0.1700
Data Index: 4751760 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19