Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.7008. Min Act: -0.1700
Data Index: 2485451 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.3258. Min Act: -0.1700
Data Index: 8099935 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.2633. Min Act: -0.1700
Data Index: 8799477 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.2633. Min Act: -0.1700
Data Index: 2122601 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.2008. Min Act: -0.1700
Data Index: 5468620 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.2008. Min Act: -0.1700
Data Index: 1723711 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.1695. Min Act: -0.1700
Data Index: 4738887 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.1383. Min Act: -0.1700
Data Index: 7229798 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.0133. Min Act: -0.1700
Data Index: 5953425 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7008. Min Range: -8.7008
Max Act: 8.0133. Min Act: -0.1700
Data Index: 1331629 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9508. Min Act: -0.1700
Data Index: 7562953 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9508. Min Act: -0.1700
Data Index: 796733 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9508. Min Act: -0.1700
Data Index: 5345106 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9508. Min Act: -0.1700
Data Index: 1837074 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9195. Min Act: -0.1700
Data Index: 6745796 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9195. Min Act: -0.1700
Data Index: 2712801 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.9195. Min Act: -0.1700
Data Index: 4463005 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.8883. Min Act: -0.1700
Data Index: 5014054 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.8570. Min Act: -0.1700
Data Index: 233672 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7008. Min Range: -8.7008
Max Act: 7.8883. Min Act: -0.1700
Data Index: 3251604 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19