Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.5435. Min Act: -0.1700
Data Index: 5904985 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.1373. Min Act: -0.1700
Data Index: 7371424 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0748. Min Act: -0.1700
Data Index: 8371889 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0123. Min Act: -0.1700
Data Index: 8607324 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5435. Min Range: -6.5435
Max Act: 6.0123. Min Act: -0.1700
Data Index: 3420812 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.9810. Min Act: -0.1700
Data Index: 6827461 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.9498. Min Act: -0.1700
Data Index: 5558028 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8873. Min Act: -0.1700
Data Index: 4851898 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8560. Min Act: -0.1700
Data Index: 4227443 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8560. Min Act: -0.1700
Data Index: 7324528 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8560. Min Act: -0.1700
Data Index: 7638207 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8560. Min Act: -0.1700
Data Index: 987735 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8248. Min Act: -0.1700
Data Index: 6926674 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7935. Min Act: -0.1700
Data Index: 5951182 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8751120 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.8248. Min Act: -0.1700
Data Index: 8738071 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8192851 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7623. Min Act: -0.1700
Data Index: 7916733 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7935. Min Act: -0.1700
Data Index: 4844636 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5435. Min Range: -6.5435
Max Act: 5.7623. Min Act: -0.1700
Data Index: 1180310 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19