Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.8551. Min Act: -0.1700
Data Index: 1504814 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1972684 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6676. Min Act: -0.1700
Data Index: 896503 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6989. Min Act: -0.1700
Data Index: 5014432 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6676. Min Act: -0.1700
Data Index: 2572121 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6676. Min Act: -0.1700
Data Index: 5913160 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6364. Min Act: -0.1700
Data Index: 3928383 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6051. Min Act: -0.1700
Data Index: 331588 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.6051. Min Act: -0.1700
Data Index: 2221954 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.5739. Min Act: -0.1700
Data Index: 8065910 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.5739. Min Act: -0.1700
Data Index: 919106 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.5426. Min Act: -0.1700
Data Index: 2143180 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.5426. Min Act: -0.1700
Data Index: 8518953 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4801. Min Act: -0.1700
Data Index: 5380490 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.5114. Min Act: -0.1700
Data Index: 4464762 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4801. Min Act: -0.1700
Data Index: 8671313 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4489. Min Act: -0.1700
Data Index: 3726751 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4801. Min Act: -0.1700
Data Index: 6520208 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4489. Min Act: -0.1700
Data Index: 2009839 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8551. Min Range: -4.8551
Max Act: 4.4489. Min Act: -0.1700
Data Index: 5343969 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19