Model: None
Dataset: The Pile
Neuron 833 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.3668. Min Act: -0.1700
Data Index: 7758448 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.3511. Min Act: -0.1700
Data Index: 7330184 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2883. Min Act: -0.1700
Data Index: 284567 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2726. Min Act: -0.1700
Data Index: 3813197 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2726. Min Act: -0.1700
Data Index: 3257535 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2726. Min Act: -0.1700
Data Index: 6684270 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2569. Min Act: -0.1700
Data Index: 6299616 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2569. Min Act: -0.1700
Data Index: 10082590 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2412. Min Act: -0.1700
Data Index: 5728625 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.2097. Min Act: -0.1700
Data Index: 2513244 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1940. Min Act: -0.1700
Data Index: 6157219 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1940. Min Act: -0.1700
Data Index: 8652830 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1940. Min Act: -0.1700
Data Index: 120035 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 1134771 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 5871130 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 9011246 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 9497756 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 9755944 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 9928000 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1782. Min Act: -0.1700
Data Index: 7208107 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19