Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0133. Min Range: -8.0133
Max Act: 8.0133. Min Act: -0.1700
Data Index: 6068996 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0133. Min Range: -8.0133
Max Act: 8.0133. Min Act: -0.1700
Data Index: 1397256 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.9508. Min Act: -0.1700
Data Index: 5628341 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.9508. Min Act: -0.1700
Data Index: 621846 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.8258. Min Act: -0.1700
Data Index: 6940701 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.8570. Min Act: -0.1700
Data Index: 6693676 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.7320. Min Act: -0.1700
Data Index: 913874 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.7633. Min Act: -0.1700
Data Index: 5998541 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.7320. Min Act: -0.1700
Data Index: 3668158 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.7008. Min Act: -0.1700
Data Index: 4319186 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.7008. Min Act: -0.1700
Data Index: 6656719 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6695. Min Act: -0.1700
Data Index: 3122546 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6695. Min Act: -0.1700
Data Index: 6842893 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6383. Min Act: -0.1700
Data Index: 3174359 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6383. Min Act: -0.1700
Data Index: 3663688 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6070. Min Act: -0.1700
Data Index: 5948462 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6070. Min Act: -0.1700
Data Index: 3318231 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6070. Min Act: -0.1700
Data Index: 6494224 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6070. Min Act: -0.1700
Data Index: 5953333 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.5758. Min Act: -0.1700
Data Index: 325609 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19