Model: None
Dataset: The Pile
Neuron 484 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.7164. Min Act: -0.1619
Data Index: 6452097 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6363. Min Act: -0.1698
Data Index: 10139392 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6523. Min Act: -0.1700
Data Index: 4382295 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6523. Min Act: -0.1700
Data Index: 3392998 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6202. Min Act: -0.1699
Data Index: 9744884 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6041. Min Act: -0.1700
Data Index: 1878160 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6202. Min Act: -0.1690
Data Index: 1886007 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1698
Data Index: 7655805 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.6041. Min Act: -0.1699
Data Index: 1244107 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5719. Min Act: -0.1604
Data Index: 2395151 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1670
Data Index: 903300 (The Pile)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1697
Data Index: 2012637 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5719. Min Act: -0.1697
Data Index: 177482 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1615
Data Index: 10469647 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5397. Min Act: -0.1692
Data Index: 6305788 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5397. Min Act: -0.1699
Data Index: 2550607 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1694
Data Index: 1917125 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5397. Min Act: -0.1700
Data Index: 5293025 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1699
Data Index: 4641622 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7164. Min Range: -2.7164
Max Act: 2.5558. Min Act: -0.1700
Data Index: 998045 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19