Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1184. Min Range: -7.1184
Max Act: 7.1184. Min Act: -0.1700
Data Index: 1863579 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1184. Min Range: -7.1184
Max Act: 7.1184. Min Act: -0.1700
Data Index: 4075845 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1184. Min Range: -7.1184
Max Act: 7.0872. Min Act: -0.1700
Data Index: 4827159 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1184. Min Range: -7.1184
Max Act: 7.0559. Min Act: -0.1700
Data Index: 1859719 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.9934. Min Act: -0.1700
Data Index: 2721563 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8684. Min Act: -0.1700
Data Index: 6935211 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8684. Min Act: -0.1700
Data Index: 126852 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8372. Min Act: -0.1700
Data Index: 7412393 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8059. Min Act: -0.1700
Data Index: 586286 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8372. Min Act: -0.1700
Data Index: 8116095 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.7747. Min Act: -0.1700
Data Index: 1838418 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.7122. Min Act: -0.1700
Data Index: 2102175 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6809. Min Act: -0.1700
Data Index: 5431716 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6809. Min Act: -0.1700
Data Index: 7147524 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6809. Min Act: -0.1700
Data Index: 573427 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6809. Min Act: -0.1700
Data Index: 5510390 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6497. Min Act: -0.1700
Data Index: 7030362 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6497. Min Act: -0.1700
Data Index: 668238 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6497. Min Act: -0.1700
Data Index: 378345 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6497. Min Act: -0.1700
Data Index: 3087836 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19