Model: None
Dataset: The Pile
Neuron 1875 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0767. Min Range: -3.0767
Max Act: 3.0767. Min Act: -0.1700
Data Index: 1277472 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.9186. Min Act: -0.1700
Data Index: 5404148 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.9027. Min Act: -0.1700
Data Index: 2370370 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8869. Min Act: -0.1700
Data Index: 5564896 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8869. Min Act: -0.1700
Data Index: 9136017 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8869. Min Act: -0.1700
Data Index: 6238949 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8710. Min Act: -0.1700
Data Index: 5712708 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8710. Min Act: -0.1700
Data Index: 5220294 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8710. Min Act: -0.1700
Data Index: 5393499 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8551. Min Act: -0.1700
Data Index: 728547 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8551. Min Act: -0.1700
Data Index: 1773378 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8551. Min Act: -0.1700
Data Index: 1630343 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8392. Min Act: -0.1700
Data Index: 2004639 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8233. Min Act: -0.1700
Data Index: 8671912 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8233. Min Act: -0.1700
Data Index: 3723564 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8074. Min Act: -0.1700
Data Index: 2530577 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8074. Min Act: -0.1700
Data Index: 5889579 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.8074. Min Act: -0.1700
Data Index: 1183879 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.7915. Min Act: -0.1700
Data Index: 1548138 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0767. Min Range: -3.0767
Max Act: 2.7755. Min Act: -0.1700
Data Index: 2160490 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19