Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4648. Min Range: -9.4648
Max Act: 9.4648. Min Act: -0.1700
Data Index: 2748530 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.9648. Min Act: -0.1700
Data Index: 6108155 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4648. Min Range: -9.4648
Max Act: 9.0273. Min Act: -0.1700
Data Index: 3379305 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.9023. Min Act: -0.1700
Data Index: 4423883 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.9023. Min Act: -0.1700
Data Index: 5523486 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 5753648 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 4392963 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 5628493 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 3296290 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 5206682 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7773. Min Act: -0.1700
Data Index: 671835 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.7148. Min Act: -0.1700
Data Index: 2038290 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.6523. Min Act: -0.1700
Data Index: 2959491 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.6523. Min Act: -0.1700
Data Index: 3975002 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.5898. Min Act: -0.1700
Data Index: 2528859 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.6523. Min Act: -0.1700
Data Index: 8277062 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.5898. Min Act: -0.1700
Data Index: 7487060 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.5898. Min Act: -0.1700
Data Index: 6986523 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.5898. Min Act: -0.1700
Data Index: 6219452 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4648. Min Range: -9.4648
Max Act: 8.5898. Min Act: -0.1700
Data Index: 2163950 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19