Model: None
Dataset: The Pile
Neuron 820 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.2341. Min Act: -0.1700
Data Index: 8904134 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.2966. Min Act: -0.1700
Data Index: 8683952 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5779. Min Range: -4.5779
Max Act: 3.8902. Min Act: -0.1700
Data Index: 429839 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.2966. Min Act: -0.1700
Data Index: 5520395 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 9808563 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.5779. Min Act: -0.1700
Data Index: 2003369 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 3082026 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5779. Min Range: -4.5779
Max Act: 3.8902. Min Act: -0.1700
Data Index: 6522241 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1091. Min Act: -0.1700
Data Index: 3568123 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 6710078 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 2753373 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.0778. Min Act: -0.1700
Data Index: 834384 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 317251 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.2028. Min Act: -0.1700
Data Index: 4651837 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5779. Min Range: -4.5779
Max Act: 3.9840. Min Act: -0.1700
Data Index: 4357119 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.0465. Min Act: -0.1700
Data Index: 10279177 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.0153. Min Act: -0.1700
Data Index: 9653329 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.0465. Min Act: -0.1700
Data Index: 7622914 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1403. Min Act: -0.1700
Data Index: 708154 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.1091. Min Act: -0.1700
Data Index: 7061723 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19