Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5197 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.9688. Min Act: -0.1700
Data Index: 1035710 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.9063. Min Act: -0.1700
Data Index: 8611723 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.7188. Min Act: -0.1700
Data Index: 25158 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.6563. Min Act: -0.1700
Data Index: 6718546 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.5938. Min Act: -0.1700
Data Index: 5876168 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4688. Min Act: -0.1700
Data Index: 1550034 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4688. Min Act: -0.1700
Data Index: 3170902 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 7990889 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 1522307 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 2909273 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 1767900 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 5493333 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.4063. Min Act: -0.1700
Data Index: 4557386 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.3438. Min Act: -0.1700
Data Index: 3034085 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.3438. Min Act: -0.1700
Data Index: 679533 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.3438. Min Act: -0.1700
Data Index: 6681208 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.3438. Min Act: -0.1700
Data Index: 5802179 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.2813. Min Act: -0.1700
Data Index: 2280853 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.2813. Min Act: -0.1700
Data Index: 3876289 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9688. Min Range: -8.9688
Max Act: 8.2813. Min Act: -0.1700
Data Index: 2144594 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19