Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.6791. Min Act: -0.1700
Data Index: 3027108 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.3666. Min Act: -0.1700
Data Index: 910511 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.1791. Min Act: -0.1700
Data Index: 5273659 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.1479. Min Act: -0.1700
Data Index: 699488 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.1166. Min Act: -0.1700
Data Index: 2475080 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8666. Min Act: -0.1700
Data Index: 5479077 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.7729. Min Act: -0.1700
Data Index: 5526042 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8041. Min Act: -0.1700
Data Index: 4796171 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.7729. Min Act: -0.1700
Data Index: 7112274 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.7104. Min Act: -0.1700
Data Index: 8803301 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.7416. Min Act: -0.1700
Data Index: 3142233 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.7104. Min Act: -0.1700
Data Index: 890833 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6791. Min Act: -0.1700
Data Index: 4702017 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 7680787 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 6170637 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 784169 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 4407608 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6166. Min Act: -0.1700
Data Index: 4497869 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6479. Min Act: -0.1700
Data Index: 8083951 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.6166. Min Act: -0.1700
Data Index: 2340838 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19