Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.5082. Min Act: -0.1700
Data Index: 396575 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.1957. Min Act: -0.1700
Data Index: 4647940 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.1020. Min Act: -0.1700
Data Index: 613808 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.0082. Min Act: -0.1700
Data Index: 3404501 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.0082. Min Act: -0.1700
Data Index: 5742763 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3236560 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.0082. Min Act: -0.1700
Data Index: 7248252 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9770. Min Act: -0.1700
Data Index: 53430 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9770. Min Act: -0.1700
Data Index: 2303123 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9457. Min Act: -0.1700
Data Index: 3059011 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8832. Min Act: -0.1700
Data Index: 8426414 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8520. Min Act: -0.1700
Data Index: 2865962 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3188199 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 7046562 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 6346849 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2886310 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 6924727 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 184656 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 2980714 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7270. Min Act: -0.1700
Data Index: 7766415 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19