Model: None
Dataset: The Pile
Neuron 871 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.7551. Min Act: -0.1700
Data Index: 7724221 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6612. Min Act: -0.1676
Data Index: 2808273 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6142. Min Act: -0.1680
Data Index: 4887857 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6299. Min Act: -0.1699
Data Index: 9497461 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5986. Min Act: -0.1700
Data Index: 5678092 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6142. Min Act: -0.1699
Data Index: 7206351 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5203. Min Act: -0.1664
Data Index: 9190955 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6142. Min Act: -0.0987
Data Index: 7002556 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5516. Min Act: -0.1693
Data Index: 661297 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5203. Min Act: -0.1698
Data Index: 2179321 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5516. Min Act: -0.1556
Data Index: 8506919 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5672. Min Act: -0.0779
Data Index: 3922373 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6455. Min Act: -0.1699
Data Index: 2048729 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5829. Min Act: -0.1535
Data Index: 879355 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5986. Min Act: -0.1700
Data Index: 9341359 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5829. Min Act: -0.1700
Data Index: 6206078 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5672. Min Act: -0.1695
Data Index: 8526088 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5516. Min Act: -0.1700
Data Index: 1277194 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5359. Min Act: -0.1699
Data Index: 8327708 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.4576. Min Act: -0.1691
Data Index: 5267244 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19