Model: None
Dataset: The Pile
Neuron 1888 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.6070. Min Act: -0.1700
Data Index: 396097 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5426. Min Act: -0.1700
Data Index: 9236990 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5102. Min Act: -0.1700
Data Index: 9094679 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5264. Min Act: -0.1700
Data Index: 814932 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5264. Min Act: -0.1700
Data Index: 4046410 (The Pile)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5102. Min Act: -0.1700
Data Index: 6620600 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.5264. Min Act: -0.1700
Data Index: 4391355 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 5778167 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4778. Min Act: -0.1700
Data Index: 3068203 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4778. Min Act: -0.1700
Data Index: 3065678 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 10352599 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4778. Min Act: -0.1700
Data Index: 10490121 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4444554 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4778. Min Act: -0.1700
Data Index: 3165238 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4616. Min Act: -0.1700
Data Index: 2692324 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 2697919 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 5253283 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4778. Min Act: -0.1700
Data Index: 2554017 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4940. Min Act: -0.1700
Data Index: 395068 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6070. Min Range: -2.6070
Max Act: 2.4616. Min Act: -0.1700
Data Index: 5589853 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19