Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0644. Min Range: -5.0644
Max Act: 5.0644. Min Act: -0.1700
Data Index: 4323444 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.9394. Min Act: -0.1700
Data Index: 1596903 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.9394. Min Act: -0.1700
Data Index: 2955682 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8769. Min Act: -0.1700
Data Index: 5364990 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8769. Min Act: -0.1700
Data Index: 2477419 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8457. Min Act: -0.1700
Data Index: 7586911 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8457. Min Act: -0.1700
Data Index: 2625746 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8457. Min Act: -0.1700
Data Index: 664114 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8144. Min Act: -0.1700
Data Index: 6181570 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.8144. Min Act: -0.1700
Data Index: 7554696 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 7163833 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 6846972 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 4747462 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 7563449 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 5650720 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 143742 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 2061566 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7831. Min Act: -0.1700
Data Index: 1037341 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4638303 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0644. Min Range: -5.0644
Max Act: 4.7206. Min Act: -0.1700
Data Index: 2212886 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19