Model: None
Dataset: The Pile
Neuron 1718 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.0400. Min Act: -0.0543
Data Index: 6664614 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.1025. Min Act: -0.1699
Data Index: 3114257 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.0400. Min Act: 0.1924
Data Index: 7181993 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.6338. Min Act: -0.1373
Data Index: 8306042 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.4463. Min Act: 0.1237
Data Index: 3365170 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.9775. Min Act: -0.1156
Data Index: 1284626 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.0713. Min Act: -0.1070
Data Index: 4535067 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.6338. Min Act: 0.0420
Data Index: 10133124 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.0400. Min Act: -0.1698
Data Index: 8436647 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.4463. Min Act: 0.2218
Data Index: 1636501 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.2588. Min Act: -0.1700
Data Index: 2141610 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6338. Min Range: -8.6338
Max Act: 6.6338. Min Act: -0.1675
Data Index: 5937688 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.1963. Min Act: 0.2570
Data Index: 5839387 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6338. Min Range: -8.6338
Max Act: 8.3838. Min Act: 0.1449
Data Index: 2573966 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.1025. Min Act: -0.1446
Data Index: 8890782 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.1963. Min Act: -0.1389
Data Index: 4283058 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.1963. Min Act: -0.1675
Data Index: 10077975 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6338. Min Range: -8.6338
Max Act: 7.0088. Min Act: 0.0860
Data Index: 8264136 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6338. Min Range: -8.6338
Max Act: 4.3994. Min Act: -0.1666
Data Index: 10374863 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6338. Min Range: -8.6338
Max Act: 6.6025. Min Act: -0.1699
Data Index: 3770668 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19