Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 434 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0497. Min Range: -8.0497
Max Act: 8.0497. Min Act: -0.1700
Data Index: 2582914 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.9247. Min Act: -0.1700
Data Index: 6720345 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.8935. Min Act: -0.1700
Data Index: 2377346 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.8935. Min Act: -0.1700
Data Index: 1926400 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.7685. Min Act: -0.1700
Data Index: 4024666 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.6747. Min Act: -0.1700
Data Index: 3395431 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.6435. Min Act: -0.1700
Data Index: 7907361 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5810. Min Act: -0.1700
Data Index: 3424177 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.6122. Min Act: -0.1700
Data Index: 2174777 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5810. Min Act: -0.1700
Data Index: 2523899 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5810. Min Act: -0.1700
Data Index: 1133220 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5810. Min Act: -0.1700
Data Index: 6540894 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5185. Min Act: -0.1700
Data Index: 4729997 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.5185. Min Act: -0.1700
Data Index: 867668 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4872. Min Act: -0.1700
Data Index: 4879321 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4560. Min Act: -0.1700
Data Index: 6854010 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4560. Min Act: -0.1700
Data Index: 7444334 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4247. Min Act: -0.1700
Data Index: 709457 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4560. Min Act: -0.1700
Data Index: 5483722 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0497. Min Range: -8.0497
Max Act: 7.4247. Min Act: -0.1700
Data Index: 1177138 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19