Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1884 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.5219. Min Act: -0.1700
Data Index: 3821060 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.4594. Min Act: -0.1700
Data Index: 4750835 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.4281. Min Act: -0.1700
Data Index: 1769658 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3344. Min Act: -0.1700
Data Index: 4754120 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3344. Min Act: -0.1700
Data Index: 8267992 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3344. Min Act: -0.1700
Data Index: 2381799 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.3031. Min Act: -0.1700
Data Index: 892611 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 2106267 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2719. Min Act: -0.1700
Data Index: 7377927 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 5957083 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2406. Min Act: -0.1700
Data Index: 7471986 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 5129326 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 1165325 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 6799126 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 1284923 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.1781. Min Act: -0.1700
Data Index: 6792653 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.1781. Min Act: -0.1700
Data Index: 1918759 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.2094. Min Act: -0.1700
Data Index: 3132446 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.1781. Min Act: -0.1700
Data Index: 6043114 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5219. Min Range: -4.5219
Max Act: 4.1781. Min Act: -0.1700
Data Index: 8376800 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19