Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0508. Min Range: -5.0508
Max Act: 5.0508. Min Act: -0.1700
Data Index: 2718307 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0508. Min Range: -5.0508
Max Act: 5.0508. Min Act: -0.1700
Data Index: 1914372 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.9258. Min Act: -0.1700
Data Index: 2610859 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8946. Min Act: -0.1700
Data Index: 8709998 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7348034 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8321. Min Act: -0.1700
Data Index: 4553580 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 5236717 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 2310529 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 1593403 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 740723 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 1775268 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 6626503 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.8008. Min Act: -0.1700
Data Index: 2010128 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7696. Min Act: -0.1700
Data Index: 912057 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7696. Min Act: -0.1700
Data Index: 2005346 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7383. Min Act: -0.1700
Data Index: 5459805 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7383. Min Act: -0.1700
Data Index: 1807668 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7383. Min Act: -0.1700
Data Index: 7187990 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7383. Min Act: -0.1700
Data Index: 2221268 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0508. Min Range: -5.0508
Max Act: 4.7071. Min Act: -0.1700
Data Index: 5384475 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19