Model: None
Dataset: The Pile
Neuron 1719 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.8032. Min Act: -0.1700
Data Index: 142898 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7873. Min Act: -0.1700
Data Index: 4482116 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7713. Min Act: -0.1700
Data Index: 6054538 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7713. Min Act: -0.1700
Data Index: 7490835 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7554. Min Act: -0.1700
Data Index: 9302138 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7234. Min Act: -0.1700
Data Index: 6962917 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7234. Min Act: -0.1700
Data Index: 1617813 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7075. Min Act: -0.1700
Data Index: 8027917 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7075. Min Act: -0.1700
Data Index: 10670729 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.7075. Min Act: -0.1700
Data Index: 8620276 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6914. Min Act: -0.1700
Data Index: 853777 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6914. Min Act: -0.1700
Data Index: 4186405 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6914. Min Act: -0.1700
Data Index: 10507650 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6914. Min Act: -0.1700
Data Index: 8378848 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6754. Min Act: -0.1700
Data Index: 5640054 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6594. Min Act: -0.1700
Data Index: 5121579 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6594. Min Act: -0.1700
Data Index: 5191349 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6594. Min Act: -0.1700
Data Index: 6791642 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6594. Min Act: -0.1700
Data Index: 5567115 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8032. Min Range: -2.8032
Max Act: 2.6594. Min Act: -0.1700
Data Index: 970444 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19