Model: None
Dataset: The Pile
Neuron 644 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.4154. Min Act: -0.1651
Data Index: 10719279 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.4779. Min Act: -0.1643
Data Index: 602915 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.3529. Min Act: -0.1695
Data Index: 4060312 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1341. Min Act: -0.1662
Data Index: 10436000 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.2591. Min Act: -0.1633
Data Index: 2096456 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.3529. Min Act: -0.1609
Data Index: 3043368 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.2279. Min Act: -0.1627
Data Index: 6532539 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.3529. Min Act: -0.1646
Data Index: 7416169 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.3216. Min Act: -0.1699
Data Index: 9968672 (The Pile)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.3216. Min Act: -0.1637
Data Index: 4103068 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1029. Min Act: -0.1651
Data Index: 1896885 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.2904. Min Act: -0.1700
Data Index: 7316447 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1966. Min Act: -0.1643
Data Index: 4140576 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.0404. Min Act: -0.1612
Data Index: 7341836 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.2279. Min Act: -0.1654
Data Index: 10429054 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1966. Min Act: -0.1686
Data Index: 10137926 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1966. Min Act: -0.1643
Data Index: 5704551 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1029. Min Act: -0.1623
Data Index: 3599503 (The Pile)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.1654. Min Act: -0.1690
Data Index: 1698251 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4779. Min Range: -7.4779
Max Act: 7.0716. Min Act: -0.1683
Data Index: 1585766 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19