Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6045 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.8245. Min Act: -0.1700
Data Index: 2637434 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.7620. Min Act: -0.1700
Data Index: 5784526 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6995. Min Act: -0.1700
Data Index: 2488409 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6370. Min Act: -0.1700
Data Index: 2887283 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6683. Min Act: -0.1700
Data Index: 3345794 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6370. Min Act: -0.1700
Data Index: 168949 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6683. Min Act: -0.1700
Data Index: 8019813 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.6058. Min Act: -0.1700
Data Index: 6466297 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5745. Min Act: -0.1700
Data Index: 1530731 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5745. Min Act: -0.1700
Data Index: 4748998 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5433. Min Act: -0.1700
Data Index: 5376552 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5433. Min Act: -0.1700
Data Index: 2531337 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5433. Min Act: -0.1700
Data Index: 8548275 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5433. Min Act: -0.1700
Data Index: 8241790 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5433. Min Act: -0.1700
Data Index: 1974369 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4163623 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5120. Min Act: -0.1700
Data Index: 1815251 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4387996 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4810609 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8245. Min Range: -4.8245
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4899260 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19