Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.6406. Min Act: -0.1700
Data Index: 265000 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.5156. Min Act: -0.1700
Data Index: 7900869 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.3906. Min Act: -0.1700
Data Index: 5550918 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.2344. Min Act: -0.1700
Data Index: 2979175 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.1719. Min Act: -0.1700
Data Index: 4290380 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.1719. Min Act: -0.1700
Data Index: 2263546 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7920419 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7513498 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 1765415 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 6798346 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 5293921 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 4884572 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 1413931 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0781. Min Act: -0.1700
Data Index: 4715422 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0469. Min Act: -0.1700
Data Index: 7900860 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0469. Min Act: -0.1700
Data Index: 1647596 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0156. Min Act: -0.1700
Data Index: 926889 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0469. Min Act: -0.1700
Data Index: 70741 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0156. Min Act: -0.1700
Data Index: 2135382 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6406. Min Range: -5.6406
Max Act: 5.0156. Min Act: -0.1700
Data Index: 7706459 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19