Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1826. Min Range: -7.1826
Max Act: 7.1826. Min Act: -0.1700
Data Index: 713659 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1826. Min Range: -7.1826
Max Act: 7.1201. Min Act: -0.1700
Data Index: 8309222 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1826. Min Range: -7.1826
Max Act: 7.0576. Min Act: -0.1700
Data Index: 696784 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1826. Min Range: -7.1826
Max Act: 7.0888. Min Act: -0.1700
Data Index: 142790 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9638. Min Act: -0.1700
Data Index: 6641771 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6705148 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9326. Min Act: -0.1700
Data Index: 3585457 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6516508 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9326. Min Act: -0.1700
Data Index: 7768591 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9013. Min Act: -0.1700
Data Index: 8117339 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9013. Min Act: -0.1700
Data Index: 4895820 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.9013. Min Act: -0.1700
Data Index: 871801 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.8701. Min Act: -0.1700
Data Index: 8319236 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.8701. Min Act: -0.1700
Data Index: 1600882 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.8701. Min Act: -0.1700
Data Index: 250254 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.8076. Min Act: -0.1700
Data Index: 1546803 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.7763. Min Act: -0.1700
Data Index: 2394652 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.7763. Min Act: -0.1700
Data Index: 7022396 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.7451. Min Act: -0.1700
Data Index: 6015299 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1826. Min Range: -7.1826
Max Act: 6.7451. Min Act: -0.1700
Data Index: 7714841 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19