Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0905. Min Range: -5.0905
Max Act: 5.0905. Min Act: -0.1700
Data Index: 1778484 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.9030. Min Act: -0.1700
Data Index: 3730690 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.8405. Min Act: -0.1700
Data Index: 6841236 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.8092. Min Act: -0.1700
Data Index: 8699329 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7780. Min Act: -0.1700
Data Index: 3730695 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7467. Min Act: -0.1700
Data Index: 6182865 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7467. Min Act: -0.1700
Data Index: 3730696 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7155. Min Act: -0.1700
Data Index: 7814570 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7155. Min Act: -0.1700
Data Index: 4105187 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7155. Min Act: -0.1700
Data Index: 5793825 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.7155. Min Act: -0.1700
Data Index: 6979830 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6842. Min Act: -0.1700
Data Index: 7912339 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6842. Min Act: -0.1700
Data Index: 5974779 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6530. Min Act: -0.1700
Data Index: 6714214 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6217. Min Act: -0.1700
Data Index: 7237049 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6217. Min Act: -0.1700
Data Index: 1281961 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.6217. Min Act: -0.1700
Data Index: 641798 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.5905. Min Act: -0.1700
Data Index: 2528645 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5419692 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0905. Min Range: -5.0905
Max Act: 4.5905. Min Act: -0.1700
Data Index: 27357 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19