Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6125 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.3534. Min Act: -0.1700
Data Index: 4299695 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.3847. Min Act: -0.1700
Data Index: 6980012 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.3222. Min Act: -0.1700
Data Index: 5611946 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.2909. Min Act: -0.1700
Data Index: 1046273 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.2597. Min Act: -0.1700
Data Index: 4764915 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1972. Min Act: -0.1699
Data Index: 2700716 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.2284. Min Act: -0.1700
Data Index: 4856664 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1347. Min Act: -0.1700
Data Index: 4624048 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1034. Min Act: -0.1700
Data Index: 3557433 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1347. Min Act: -0.1688
Data Index: 2117576 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1034. Min Act: -0.1699
Data Index: 1967727 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.1034. Min Act: -0.1695
Data Index: 1036747 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.0097. Min Act: -0.1697
Data Index: 5213466 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.9784. Min Act: -0.1646
Data Index: 6302207 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 3663987 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.9784. Min Act: -0.1700
Data Index: 5339281 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3847. Min Range: -8.3847
Max Act: 8.0097. Min Act: -0.1700
Data Index: 8755778 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 8262766 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.9159. Min Act: -0.1695
Data Index: 2854301 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3847. Min Range: -8.3847
Max Act: 7.8847. Min Act: -0.1700
Data Index: 8423607 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19