Model: None
Dataset: The Pile
Neuron 1715 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.1164. Min Range: -4.1164
Max Act: 4.1164. Min Act: -0.1699
Data Index: 8814569 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.9132. Min Act: -0.1700
Data Index: 6209678 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8976. Min Act: -0.1698
Data Index: 10197729 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8819. Min Act: -0.1674
Data Index: 10011205 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8976. Min Act: -0.1700
Data Index: 10001798 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8819. Min Act: -0.1699
Data Index: 1097650 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8350. Min Act: -0.1695
Data Index: 954379 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1674
Data Index: 10448863 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1699
Data Index: 1737538 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1683
Data Index: 10266138 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7881. Min Act: -0.1699
Data Index: 7737494 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1674
Data Index: 3492318 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1698
Data Index: 327478 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7881. Min Act: -0.1674
Data Index: 7715589 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7881. Min Act: -0.1674
Data Index: 457939 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.8037. Min Act: -0.1674
Data Index: 9103342 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7881. Min Act: -0.1699
Data Index: 1306891 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7881. Min Act: -0.1700
Data Index: 7524690 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7724. Min Act: -0.1696
Data Index: 7727388 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1164. Min Range: -4.1164
Max Act: 3.7724. Min Act: -0.1700
Data Index: 4046575 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19