Model: None
Dataset: The Pile
Neuron 3987 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.8063. Min Act: -0.1700
Data Index: 830179 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7907. Min Act: -0.1700
Data Index: 3683694 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7750. Min Act: -0.1700
Data Index: 10068146 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7594. Min Act: -0.1700
Data Index: 5030082 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7437. Min Act: -0.1700
Data Index: 3612840 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7437. Min Act: -0.1700
Data Index: 4355033 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7281. Min Act: -0.1700
Data Index: 1057957 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7124. Min Act: -0.1700
Data Index: 854176 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.7124. Min Act: -0.1700
Data Index: 5697499 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 8040046 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 3410492 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 8026046 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 8172361 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 7639313 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 1715397 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 3608820 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 3038923 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6968. Min Act: -0.1700
Data Index: 8661574 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6811. Min Act: -0.1700
Data Index: 2569748 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8063. Min Range: -3.8063
Max Act: 3.6811. Min Act: -0.1700
Data Index: 5017249 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19