Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.9661. Min Act: -0.1700
Data Index: 1599852 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.9036. Min Act: -0.1700
Data Index: 7933423 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.8724. Min Act: -0.1700
Data Index: 3120305 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.9036. Min Act: -0.1700
Data Index: 2769035 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.8099. Min Act: -0.1700
Data Index: 886043 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.8411. Min Act: -0.1700
Data Index: 10242 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.7786. Min Act: -0.1700
Data Index: 4433069 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.7161. Min Act: -0.1700
Data Index: 4047825 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.7161. Min Act: -0.1700
Data Index: 4998258 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.7161. Min Act: -0.1700
Data Index: 1624137 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6849. Min Act: -0.1700
Data Index: 4482218 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 4739614 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 698249 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 199798 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 682214 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5527882 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 8656236 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6224. Min Act: -0.1700
Data Index: 2832621 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6224. Min Act: -0.1700
Data Index: 1907197 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9661. Min Range: -5.9661
Max Act: 5.6536. Min Act: -0.1700
Data Index: 6400710 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19