Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0968. Min Range: -1.0968
Max Act: 1.0968. Min Act: -0.1700
Data Index: 4743126 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0968. Min Range: -1.0968
Max Act: 1.0095. Min Act: -0.1685
Data Index: 6862722 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9922. Min Act: -0.1700
Data Index: 4247619 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9403. Min Act: -0.1699
Data Index: 8271614 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9490. Min Act: -0.1700
Data Index: 4084860 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9317. Min Act: -0.1700
Data Index: 1805903 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9317. Min Act: -0.1700
Data Index: 3629105 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9317. Min Act: -0.1693
Data Index: 8167426 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9317. Min Act: -0.1523
Data Index: 8139289 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9060. Min Act: -0.1694
Data Index: 4993105 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9146. Min Act: -0.1700
Data Index: 8544912 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9146. Min Act: -0.1700
Data Index: 8119964 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9060. Min Act: -0.1669
Data Index: 1791326 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9060. Min Act: -0.1700
Data Index: 1411802 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9060. Min Act: -0.1699
Data Index: 6378003 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.8974. Min Act: -0.1700
Data Index: 680910 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.8974. Min Act: -0.1696
Data Index: 6736471 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.9060. Min Act: -0.1700
Data Index: 6698734 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.8889. Min Act: -0.1693
Data Index: 5409906 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0968. Min Range: -1.0968
Max Act: 0.8804. Min Act: -0.1700
Data Index: 7634788 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19