Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 3837162 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.8309. Min Act: -0.1700
Data Index: 5985983 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.7996. Min Act: -0.1700
Data Index: 3873888 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.7684. Min Act: -0.1700
Data Index: 5135838 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.7059. Min Act: -0.1700
Data Index: 3221465 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.5809. Min Act: -0.1700
Data Index: 4985494 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.5809. Min Act: -0.1700
Data Index: 1456735 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.5809. Min Act: -0.1700
Data Index: 5041189 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.5184. Min Act: -0.1700
Data Index: 8185462 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.5184. Min Act: -0.1700
Data Index: 4246698 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.4871. Min Act: -0.1700
Data Index: 6960291 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3934. Min Act: -0.1700
Data Index: 981204 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3934. Min Act: -0.1700
Data Index: 6574696 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3934. Min Act: -0.1700
Data Index: 7796479 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3934. Min Act: -0.1700
Data Index: 7391820 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3621. Min Act: -0.1700
Data Index: 2183412 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3309. Min Act: -0.1700
Data Index: 7348649 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3934. Min Act: -0.1700
Data Index: 4246699 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3621. Min Act: -0.1700
Data Index: 1296052 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8621. Min Range: -4.8621
Max Act: 4.3309. Min Act: -0.1700
Data Index: 4907430 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19