Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4295 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8618. Min Act: -0.1700
Data Index: 4594237 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8618. Min Act: -0.1700
Data Index: 2286934 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 7704344 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2946228 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 168212 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6743. Min Act: -0.1700
Data Index: 798322 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6743. Min Act: -0.1700
Data Index: 4294175 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6743. Min Act: -0.1700
Data Index: 5379734 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7446580 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6660107 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 6776109 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7427846 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 8260693 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7894825 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 7414804 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 2009592 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 3944015 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5805. Min Act: -0.1700
Data Index: 3600352 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 2733262 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5805. Min Act: -0.1700
Data Index: 2795206 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19