Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.6034. Min Act: -0.1700
Data Index: 6868703 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.1034. Min Act: -0.1700
Data Index: 5162539 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.1659. Min Act: -0.1700
Data Index: 4159775 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.0409. Min Act: -0.1700
Data Index: 7278621 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.0409. Min Act: -0.1700
Data Index: 6512909 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.9784. Min Act: -0.1700
Data Index: 4993683 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6034. Min Range: -10.6034
Max Act: 10.0409. Min Act: -0.1700
Data Index: 2806436 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.9159. Min Act: -0.1700
Data Index: 3882493 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.9159. Min Act: -0.1700
Data Index: 7450702 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.8534. Min Act: -0.1700
Data Index: 7762961 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.8534. Min Act: -0.1700
Data Index: 1925905 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.9159. Min Act: -0.1700
Data Index: 8536127 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.8534. Min Act: -0.1700
Data Index: 7621674 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.8534. Min Act: -0.1700
Data Index: 7110006 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.7909. Min Act: -0.1700
Data Index: 7513908 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.8534. Min Act: -0.1700
Data Index: 4284617 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.7909. Min Act: -0.1700
Data Index: 7137321 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.7909. Min Act: -0.1700
Data Index: 8366904 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.7909. Min Act: -0.1700
Data Index: 3788491 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6034. Min Range: -10.6034
Max Act: 9.7284. Min Act: -0.1700
Data Index: 371405 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19