Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5242 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.9449. Min Act: -0.1700
Data Index: 4057724 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.8511. Min Act: -0.1700
Data Index: 5233996 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.8824. Min Act: -0.1700
Data Index: 6887344 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7886. Min Act: -0.1700
Data Index: 7054622 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7261. Min Act: -0.1700
Data Index: 2007813 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6949. Min Act: -0.1700
Data Index: 8652329 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7574. Min Act: -0.1700
Data Index: 5910014 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2808096 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6636. Min Act: -0.1700
Data Index: 7706251 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3434893 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6324. Min Act: -0.1700
Data Index: 4420261 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6324. Min Act: -0.1700
Data Index: 8809177 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5699. Min Act: -0.1700
Data Index: 7539255 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5699. Min Act: -0.1700
Data Index: 5367570 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6011. Min Act: -0.1700
Data Index: 897350 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5699. Min Act: -0.1700
Data Index: 2488203 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5699. Min Act: -0.1700
Data Index: 1987522 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4695779 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5386. Min Act: -0.1700
Data Index: 5457302 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5386. Min Act: -0.1700
Data Index: 2545401 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19