Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4872 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1842. Min Range: -5.1842
Max Act: 5.1842. Min Act: -0.1700
Data Index: 3860063 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1842. Min Range: -5.1842
Max Act: 5.0592. Min Act: -0.1700
Data Index: 6612088 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.9342. Min Act: -0.1700
Data Index: 8702007 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.9654. Min Act: -0.1700
Data Index: 2612014 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.9342. Min Act: -0.1700
Data Index: 8534518 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.9029. Min Act: -0.1700
Data Index: 8702004 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.8717. Min Act: -0.1700
Data Index: 8702008 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.8404. Min Act: -0.1700
Data Index: 4527591 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7779. Min Act: -0.1700
Data Index: 658125 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.8092. Min Act: -0.1700
Data Index: 8702005 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 2384795 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7467. Min Act: -0.1700
Data Index: 4601657 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 5285790 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 8702006 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 7038596 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7467. Min Act: -0.1700
Data Index: 2384792 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 8363966 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.7154. Min Act: -0.1700
Data Index: 2334431 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.6842. Min Act: -0.1700
Data Index: 1779516 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1842. Min Range: -5.1842
Max Act: 4.6842. Min Act: -0.1700
Data Index: 5133882 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19