Model: None
Dataset: The Pile
Neuron 722 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4908. Min Act: -0.1699
Data Index: 4767629 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4746. Min Act: -0.1698
Data Index: 8722768 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4584. Min Act: -0.1574
Data Index: 8075598 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4421. Min Act: -0.1698
Data Index: 1218996 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1700
Data Index: 2944733 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3932. Min Act: -0.1699
Data Index: 2947716 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3932. Min Act: -0.1700
Data Index: 585641 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1700
Data Index: 8724441 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3932. Min Act: -0.1699
Data Index: 2353662 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3769. Min Act: -0.1661
Data Index: 5840214 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1699
Data Index: 5266517 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4258. Min Act: -0.1699
Data Index: 3489677 (The Pile)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3606. Min Act: -0.1700
Data Index: 1120248 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3769. Min Act: -0.1695
Data Index: 7788267 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3932. Min Act: -0.1699
Data Index: 5603273 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3769. Min Act: -0.1700
Data Index: 1539153 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1700
Data Index: 2483603 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1700
Data Index: 2610606 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.3769. Min Act: -0.1501
Data Index: 3352803 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4908. Min Range: -2.4908
Max Act: 2.4096. Min Act: -0.1260
Data Index: 2688457 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19