Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.6720. Min Act: -0.1700
Data Index: 4468647 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.5470. Min Act: -0.1700
Data Index: 5118808 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.4845. Min Act: -0.1700
Data Index: 1507586 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.4220. Min Act: -0.1700
Data Index: 6476922 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2970. Min Act: -0.1700
Data Index: 1256129 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2345. Min Act: -0.1700
Data Index: 2730368 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2345. Min Act: -0.1700
Data Index: 3792665 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2345. Min Act: -0.1700
Data Index: 7990869 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2345. Min Act: -0.1700
Data Index: 1573133 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.2345. Min Act: -0.1700
Data Index: 6386980 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 7532771 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 7869370 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 1888221 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 4399736 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 663603 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1095. Min Act: -0.1700
Data Index: 1421654 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1720. Min Act: -0.1700
Data Index: 30072 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1095. Min Act: -0.1700
Data Index: 3723067 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1095. Min Act: -0.1700
Data Index: 6237278 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6720. Min Range: -8.6720
Max Act: 8.1095. Min Act: -0.1700
Data Index: 5193845 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19