Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1554 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.9848. Min Act: -0.1700
Data Index: 2608556 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.9223. Min Act: -0.1700
Data Index: 3531375 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.8598. Min Act: -0.1700
Data Index: 6604148 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.8598. Min Act: -0.1700
Data Index: 7865501 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.8285. Min Act: -0.1700
Data Index: 3543419 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.8285. Min Act: -0.1700
Data Index: 1307625 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 542422 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7973. Min Act: -0.1700
Data Index: 254137 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.8285. Min Act: -0.1700
Data Index: 1032079 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7348. Min Act: -0.1700
Data Index: 6017463 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 7173183 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 882561 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 6683199 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 1995527 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 4103757 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 5763944 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4685800 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.5785. Min Act: -0.1700
Data Index: 1989101 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.5785. Min Act: -0.1700
Data Index: 4714801 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.5785. Min Act: -0.1700
Data Index: 5101317 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19