Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6995. Min Range: -8.6995
Max Act: 8.6995. Min Act: -0.1700
Data Index: 8142588 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6995. Min Range: -8.6995
Max Act: 8.3870. Min Act: -0.1700
Data Index: 4405005 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6995. Min Range: -8.6995
Max Act: 8.1370. Min Act: -0.1700
Data Index: 8475552 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6995. Min Range: -8.6995
Max Act: 8.1057. Min Act: -0.1700
Data Index: 2189092 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.9807. Min Act: -0.1700
Data Index: 7023978 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.9495. Min Act: -0.1700
Data Index: 3399686 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.7932. Min Act: -0.1700
Data Index: 8653208 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6995. Min Act: -0.1700
Data Index: 6275750 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6995. Min Act: -0.1700
Data Index: 6943501 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6995. Min Act: -0.1700
Data Index: 1188112 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6682. Min Act: -0.1700
Data Index: 2840482 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6682. Min Act: -0.1700
Data Index: 3774775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.6370. Min Act: -0.1700
Data Index: 5958498 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.5745. Min Act: -0.1700
Data Index: 2807337 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.5745. Min Act: -0.1700
Data Index: 6164672 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.5432. Min Act: -0.1700
Data Index: 629594 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.5120. Min Act: -0.1700
Data Index: 4813462 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.4807. Min Act: -0.1700
Data Index: 6292247 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.4807. Min Act: -0.1700
Data Index: 2177815 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6995. Min Range: -8.6995
Max Act: 7.4807. Min Act: -0.1700
Data Index: 6649975 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19