Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0641. Min Range: -9.0641
Max Act: 9.0641. Min Act: -0.1700
Data Index: 4189786 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0641. Min Range: -9.0641
Max Act: 9.0016. Min Act: -0.1700
Data Index: 4814015 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.8766. Min Act: -0.1700
Data Index: 1687400 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.6266. Min Act: -0.1700
Data Index: 7940815 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.5641. Min Act: -0.1700
Data Index: 3925435 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.5016. Min Act: -0.1700
Data Index: 4972277 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.4391. Min Act: -0.1700
Data Index: 6788489 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.3141. Min Act: -0.1700
Data Index: 6478926 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.3141. Min Act: -0.1700
Data Index: 8586080 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.2516. Min Act: -0.1700
Data Index: 5828420 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.2516. Min Act: -0.1700
Data Index: 7721915 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1891. Min Act: -0.1700
Data Index: 8446349 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1891. Min Act: -0.1700
Data Index: 3608953 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1891. Min Act: -0.1700
Data Index: 2028651 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1891. Min Act: -0.1700
Data Index: 1628730 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1578. Min Act: -0.1700
Data Index: 8714591 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1266. Min Act: -0.1700
Data Index: 5237508 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.0953. Min Act: -0.1700
Data Index: 1889545 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.1266. Min Act: -0.1700
Data Index: 3481899 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0641. Min Range: -9.0641
Max Act: 8.0953. Min Act: -0.1700
Data Index: 4219062 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19