Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5346 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1730. Min Range: -6.1730
Max Act: 6.1730. Min Act: -0.1700
Data Index: 6507289 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1730. Min Range: -6.1730
Max Act: 6.1105. Min Act: -0.1700
Data Index: 7168871 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1730. Min Range: -6.1730
Max Act: 6.1105. Min Act: -0.1700
Data Index: 1165419 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1730. Min Range: -6.1730
Max Act: 6.0167. Min Act: -0.1700
Data Index: 2336992 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.9855. Min Act: -0.1700
Data Index: 314769 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8028425 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.8605. Min Act: -0.1700
Data Index: 7635051 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.8605. Min Act: -0.1700
Data Index: 6279893 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8006928 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.8292. Min Act: -0.1700
Data Index: 6046856 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3937364 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 6128649 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 4930497 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3932686 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3932699 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7667. Min Act: -0.1700
Data Index: 6362018 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7667. Min Act: -0.1700
Data Index: 3548646 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7667. Min Act: -0.1700
Data Index: 6909478 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7980. Min Act: -0.1700
Data Index: 1125390 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1730. Min Range: -6.1730
Max Act: 5.7667. Min Act: -0.1700
Data Index: 1443834 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19