Model: None
Dataset: The Pile
Neuron 667 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2453. Min Act: -0.1699
Data Index: 485335 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1984. Min Act: -0.1697
Data Index: 10722696 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1984. Min Act: -0.1698
Data Index: 3111140 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1828. Min Act: -0.1697
Data Index: 4946367 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1515. Min Act: -0.1687
Data Index: 596305 (The Pile)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1515. Min Act: -0.1602
Data Index: 8936570 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1202. Min Act: -0.1608
Data Index: 9945643 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1359. Min Act: -0.1636
Data Index: 8631812 (The Pile)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1681
Data Index: 9187867 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1635
Data Index: 2754265 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0734. Min Act: -0.1684
Data Index: 6692718 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1696
Data Index: 9867900 (The Pile)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0421. Min Act: -0.1697
Data Index: 3199956 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0577. Min Act: -0.1700
Data Index: 5815103 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0734. Min Act: -0.1700
Data Index: 4890778 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1641
Data Index: 9620566 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0734. Min Act: -0.1659
Data Index: 8870212 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0577. Min Act: -0.1608
Data Index: 3304853 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0421. Min Act: -0.1700
Data Index: 7641412 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0108. Min Act: -0.1678
Data Index: 8990285 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19