Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4941 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.8680. Min Act: -0.1700
Data Index: 7494039 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.8055. Min Act: -0.1700
Data Index: 8809007 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.7430. Min Act: -0.1700
Data Index: 3928959 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.6805. Min Act: -0.1700
Data Index: 1094239 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.6180. Min Act: -0.1700
Data Index: 4960204 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2279193 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.4930. Min Act: -0.1700
Data Index: 5075098 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.4305. Min Act: -0.1700
Data Index: 3898554 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.4305. Min Act: -0.1700
Data Index: 7466385 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.4305. Min Act: -0.1700
Data Index: 5555843 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.4305. Min Act: -0.1700
Data Index: 1121558 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.3680. Min Act: -0.1700
Data Index: 2343861 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.3680. Min Act: -0.1700
Data Index: 8829000 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.2430. Min Act: -0.1700
Data Index: 2237966 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.2430. Min Act: -0.1700
Data Index: 5124681 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.1805. Min Act: -0.1700
Data Index: 3980723 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.1805. Min Act: -0.1700
Data Index: 7493852 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.2430. Min Act: -0.1700
Data Index: 5555840 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.1492. Min Act: -0.1700
Data Index: 1501721 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8680. Min Range: -8.8680
Max Act: 8.1492. Min Act: -0.1700
Data Index: 4078849 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19