Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5232 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0096. Min Range: -6.0096
Max Act: 6.0096. Min Act: -0.1700
Data Index: 5322492 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.9784. Min Act: -0.1700
Data Index: 3170905 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.9784. Min Act: -0.1700
Data Index: 7390491 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.9784. Min Act: -0.1700
Data Index: 5038396 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8846. Min Act: -0.1700
Data Index: 6185234 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8846. Min Act: -0.1700
Data Index: 472996 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8534. Min Act: -0.1700
Data Index: 4023582 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2208197 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8221. Min Act: -0.1700
Data Index: 8433915 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8221. Min Act: -0.1700
Data Index: 2333236 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8221. Min Act: -0.1700
Data Index: 6354127 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.8221. Min Act: -0.1700
Data Index: 4127775 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2725246 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2183008 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7596. Min Act: -0.1700
Data Index: 4541491 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7924737 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7492540 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7909. Min Act: -0.1700
Data Index: 5439859 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7596. Min Act: -0.1700
Data Index: 505925 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0096. Min Range: -6.0096
Max Act: 5.7596. Min Act: -0.1700
Data Index: 1824901 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19