Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.3825. Min Act: -0.1700
Data Index: 8267397 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.3200. Min Act: -0.1700
Data Index: 6325261 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.2887. Min Act: -0.1700
Data Index: 3666763 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.2887. Min Act: -0.1700
Data Index: 5302965 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.2575. Min Act: -0.1700
Data Index: 7896651 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.1637. Min Act: -0.1700
Data Index: 4224947 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.1325. Min Act: -0.1700
Data Index: 7266990 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.1012. Min Act: -0.1700
Data Index: 4343804 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.1012. Min Act: -0.1700
Data Index: 4930602 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 6198860 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 7135001 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 5655649 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 7884325 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 7288274 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3825. Min Range: -7.3825
Max Act: 7.0075. Min Act: -0.1700
Data Index: 3486576 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3825. Min Range: -7.3825
Max Act: 6.9762. Min Act: -0.1700
Data Index: 5014115 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3825. Min Range: -7.3825
Max Act: 6.9762. Min Act: -0.1700
Data Index: 3075507 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3825. Min Range: -7.3825
Max Act: 6.9137. Min Act: -0.1700
Data Index: 1922493 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3825. Min Range: -7.3825
Max Act: 6.9137. Min Act: -0.1700
Data Index: 3932929 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3825. Min Range: -7.3825
Max Act: 6.8825. Min Act: -0.1700
Data Index: 171848 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19