Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7684. Min Act: -0.1700
Data Index: 1700296 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7684. Min Act: -0.1700
Data Index: 3930841 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7996. Min Act: -0.1700
Data Index: 7750595 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7371. Min Act: -0.1700
Data Index: 7541348 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7371. Min Act: -0.1700
Data Index: 1494906 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.5809. Min Act: -0.1700
Data Index: 337089 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.6121. Min Act: -0.1700
Data Index: 4023127 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.6121. Min Act: -0.1700
Data Index: 5135196 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.5809. Min Act: -0.1700
Data Index: 8333816 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.5496. Min Act: -0.1700
Data Index: 8554890 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3934. Min Act: -0.1700
Data Index: 357181 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3934. Min Act: -0.1700
Data Index: 3617276 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3621. Min Act: -0.1700
Data Index: 2038007 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3309. Min Act: -0.1700
Data Index: 7475932 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2996. Min Act: -0.1700
Data Index: 1700732 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3309. Min Act: -0.1700
Data Index: 5872000 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3621. Min Act: -0.1700
Data Index: 3295102 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3621. Min Act: -0.1700
Data Index: 2177475 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3309. Min Act: -0.1700
Data Index: 7225614 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3309. Min Act: -0.1700
Data Index: 3789937 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19