Model: None
Dataset: The Pile
Neuron 2045 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.2064. Min Act: -0.1700
Data Index: 4923441 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1749. Min Act: -0.1700
Data Index: 8768866 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1907. Min Act: -0.1700
Data Index: 9288332 (The Pile)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1749. Min Act: -0.1700
Data Index: 5418741 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1749. Min Act: -0.1700
Data Index: 1702516 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1907. Min Act: -0.1700
Data Index: 9045246 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1749. Min Act: -0.1700
Data Index: 6737137 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1592. Min Act: -0.1700
Data Index: 3862747 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1749. Min Act: -0.1700
Data Index: 5438739 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1277. Min Act: -0.1700
Data Index: 3893115 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1277. Min Act: -0.1700
Data Index: 301266 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1435. Min Act: -0.1700
Data Index: 7236266 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1119. Min Act: -0.1700
Data Index: 10750642 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1277. Min Act: -0.1700
Data Index: 2294142 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1119. Min Act: -0.1700
Data Index: 8086505 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1119. Min Act: -0.1700
Data Index: 1895548 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1277. Min Act: -0.1700
Data Index: 6252938 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1119. Min Act: -0.1700
Data Index: 9081630 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.1435. Min Act: -0.1700
Data Index: 7618395 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2064. Min Range: -3.2064
Max Act: 3.0804. Min Act: -0.1700
Data Index: 4855949 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19