Model: None
Dataset: The Pile
Neuron 1358 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.3162. Min Act: -0.1700
Data Index: 8518739 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2376. Min Act: -0.1700
Data Index: 8866002 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2376. Min Act: -0.1700
Data Index: 3558189 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2376. Min Act: -0.1700
Data Index: 3763121 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2376. Min Act: -0.1700
Data Index: 330063 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2219. Min Act: -0.1700
Data Index: 6220281 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2219. Min Act: -0.1700
Data Index: 10598873 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2219. Min Act: -0.1700
Data Index: 5906378 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2219. Min Act: -0.1700
Data Index: 1920032 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2062. Min Act: -0.1700
Data Index: 6795660 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2062. Min Act: -0.1700
Data Index: 227527 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2062. Min Act: -0.1700
Data Index: 1558812 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2062. Min Act: -0.1700
Data Index: 10448253 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2062. Min Act: -0.1700
Data Index: 9145770 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1904. Min Act: -0.1700
Data Index: 290476 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1747. Min Act: -0.1700
Data Index: 5161095 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1904. Min Act: -0.1700
Data Index: 5597893 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1904. Min Act: -0.1700
Data Index: 2831722 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1747. Min Act: -0.1700
Data Index: 4627815 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1904. Min Act: -0.1700
Data Index: 6357970 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19