Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5539 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6734. Min Range: -10.6734
Max Act: 10.6734. Min Act: -0.1700
Data Index: 1326771 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.8609. Min Act: -0.1700
Data Index: 625414 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.6109. Min Act: -0.1700
Data Index: 8152594 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 6026078 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 4851586 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 4497753 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 8500894 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 1273515 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 2473745 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 6925954 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.4234. Min Act: -0.1700
Data Index: 1476749 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.2984. Min Act: -0.1700
Data Index: 4343191 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.3609. Min Act: -0.1700
Data Index: 7228339 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.3609. Min Act: -0.1700
Data Index: 4760645 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.2984. Min Act: -0.1700
Data Index: 4747508 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.2984. Min Act: -0.1700
Data Index: 3871127 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.1734. Min Act: -0.1700
Data Index: 8695089 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.2359. Min Act: -0.1700
Data Index: 8047481 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.1734. Min Act: -0.1700
Data Index: 4729023 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6734. Min Range: -10.6734
Max Act: 9.1734. Min Act: -0.1700
Data Index: 7430444 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19