Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.8905. Min Act: -0.1700
Data Index: 2833291 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.8280. Min Act: -0.1700
Data Index: 6383256 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7655. Min Act: -0.1700
Data Index: 2471833 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7655. Min Act: -0.1700
Data Index: 5814807 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7343. Min Act: -0.1700
Data Index: 6885173 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7343. Min Act: -0.1700
Data Index: 4999302 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7030. Min Act: -0.1700
Data Index: 6223655 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7030. Min Act: -0.1700
Data Index: 7899070 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7030. Min Act: -0.1700
Data Index: 7949071 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.7030. Min Act: -0.1700
Data Index: 606482 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6718. Min Act: -0.1700
Data Index: 8292014 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6718. Min Act: -0.1700
Data Index: 3646796 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6718. Min Act: -0.1700
Data Index: 177167 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2859947 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6405. Min Act: -0.1700
Data Index: 3776450 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6405. Min Act: -0.1700
Data Index: 8435777 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6405. Min Act: -0.1700
Data Index: 4240787 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6405. Min Act: -0.1700
Data Index: 6204758 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.6092. Min Act: -0.1700
Data Index: 673804 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8905. Min Range: -4.8905
Max Act: 4.5780. Min Act: -0.1700
Data Index: 3178736 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19