Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 522 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0597. Min Range: -6.0597
Max Act: 6.0597. Min Act: -0.1700
Data Index: 2337109 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0597. Min Range: -6.0597
Max Act: 6.0285. Min Act: -0.1700
Data Index: 2176146 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.9347. Min Act: -0.1700
Data Index: 5080251 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.9035. Min Act: -0.1700
Data Index: 2859704 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.8722. Min Act: -0.1700
Data Index: 4402837 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.8410. Min Act: -0.1700
Data Index: 2129764 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.8097. Min Act: -0.1700
Data Index: 2041673 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7394795 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.7472. Min Act: -0.1700
Data Index: 2822825 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.7472. Min Act: -0.1700
Data Index: 7833532 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.7472. Min Act: -0.1700
Data Index: 4266076 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5017530 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6535. Min Act: -0.1700
Data Index: 7449560 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6535. Min Act: -0.1700
Data Index: 4887206 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2948004 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6535. Min Act: -0.1700
Data Index: 8357656 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6535. Min Act: -0.1700
Data Index: 4991664 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6847. Min Act: -0.1700
Data Index: 3199521 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6222. Min Act: -0.1700
Data Index: 6897619 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0597. Min Range: -6.0597
Max Act: 5.6222. Min Act: -0.1700
Data Index: 2289863 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19