Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1057. Min Range: -1.1057
Max Act: 1.1057. Min Act: -0.1643
Data Index: 173636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.9147. Min Act: -0.1687
Data Index: 1746483 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.8805. Min Act: -0.1671
Data Index: 6006488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.8465. Min Act: -0.1643
Data Index: 2216471 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.8296. Min Act: -0.1643
Data Index: 5692410 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.8127. Min Act: -0.1643
Data Index: 3956913 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7792. Min Act: -0.1643
Data Index: 7434568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7792. Min Act: -0.1693
Data Index: 3883650 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7626. Min Act: -0.1643
Data Index: 6831605 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7460. Min Act: -0.1643
Data Index: 6220861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7460. Min Act: -0.1696
Data Index: 7686985 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7460. Min Act: -0.1643
Data Index: 8450396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7295. Min Act: -0.1643
Data Index: 6726578 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7131. Min Act: -0.1700
Data Index: 942671 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7131. Min Act: -0.1643
Data Index: 8227766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.7131. Min Act: -0.1677
Data Index: 6308436 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.6805. Min Act: -0.1643
Data Index: 704272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.6643. Min Act: -0.1699
Data Index: 8245251 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.6643. Min Act: -0.1643
Data Index: 6643798 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1057. Min Range: -1.1057
Max Act: 0.6967. Min Act: -0.1643
Data Index: 7883518 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19