Model: None
Dataset: The Pile
Neuron 1126 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.8750. Min Act: -0.1699
Data Index: 1207508 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.0000. Min Act: -0.1699
Data Index: 7543454 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.7812. Min Act: -0.1700
Data Index: 8058820 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4705689 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.9062. Min Act: -0.1699
Data Index: 10454024 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.6562. Min Act: -0.1700
Data Index: 7995366 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.1562. Min Act: -0.1697
Data Index: 3394798 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.9375. Min Act: -0.1697
Data Index: 3400191 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.8750. Min Act: -0.1668
Data Index: 7805267 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.3750. Min Act: -0.1700
Data Index: 1130096 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.9687. Min Act: -0.1699
Data Index: 7932693 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.8750. Min Act: -0.1700
Data Index: 6237473 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.0937. Min Act: -0.1699
Data Index: 3023258 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.3437. Min Act: -0.1699
Data Index: 10153179 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.0000. Min Act: -0.1690
Data Index: 7981016 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.7500. Min Act: -0.1699
Data Index: 6680508 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.7500. Min Act: -0.1700
Data Index: 4884140 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.6250. Min Act: -0.1700
Data Index: 2805061 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8750. Min Range: -5.8750
Max Act: 4.9687. Min Act: -0.1700
Data Index: 2630490 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8750. Min Range: -5.8750
Max Act: 5.1875. Min Act: -0.1700
Data Index: 3045730 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19