Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6185. Min Range: -8.6185
Max Act: 8.6185. Min Act: -0.1700
Data Index: 1760944 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6185. Min Range: -8.6185
Max Act: 8.1185. Min Act: -0.1700
Data Index: 3947927 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6185. Min Range: -8.6185
Max Act: 8.0560. Min Act: -0.1700
Data Index: 7888746 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.7435. Min Act: -0.1700
Data Index: 4732021 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.7122. Min Act: -0.1700
Data Index: 7943388 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6810. Min Act: -0.1700
Data Index: 4240822 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6497. Min Act: -0.1700
Data Index: 6468305 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3594452 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6497. Min Act: -0.1700
Data Index: 7630169 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6497. Min Act: -0.1700
Data Index: 3607543 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.6185. Min Act: -0.1700
Data Index: 4942970 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5872. Min Act: -0.1700
Data Index: 6992859 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 6962923 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 7133191 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 5207168 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5247. Min Act: -0.1700
Data Index: 1345699 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 2430194 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1712046 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1760945 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6185. Min Range: -8.6185
Max Act: 7.5247. Min Act: -0.1700
Data Index: 6155735 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19