Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.9643. Min Act: -0.1700
Data Index: 3096163 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.5580. Min Act: -0.1700
Data Index: 6459450 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4955. Min Act: -0.1700
Data Index: 8020841 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4955. Min Act: -0.1700
Data Index: 5324256 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4643. Min Act: -0.1700
Data Index: 7782086 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4330. Min Act: -0.1700
Data Index: 1131244 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4330. Min Act: -0.1700
Data Index: 1826630 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4330. Min Act: -0.1700
Data Index: 7782077 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4018. Min Act: -0.1700
Data Index: 1796074 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4018. Min Act: -0.1700
Data Index: 5599399 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.4330. Min Act: -0.1700
Data Index: 1007917 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3705. Min Act: -0.1700
Data Index: 4944268 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3705. Min Act: -0.1700
Data Index: 7841439 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3393. Min Act: -0.1700
Data Index: 6519195 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3080. Min Act: -0.1700
Data Index: 1131242 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3393. Min Act: -0.1700
Data Index: 5061723 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.2768. Min Act: -0.1700
Data Index: 200395 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.3393. Min Act: -0.1700
Data Index: 1007927 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.2768. Min Act: -0.1700
Data Index: 5912894 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9643. Min Range: -7.9643
Max Act: 7.2768. Min Act: -0.1700
Data Index: 5639868 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19