Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4813 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.1891. Min Act: -0.1700
Data Index: 390830 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.1266. Min Act: -0.1700
Data Index: 5859419 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4340878 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4933765 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.0329. Min Act: -0.1700
Data Index: 322590 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1891. Min Range: -5.1891
Max Act: 5.0016. Min Act: -0.1700
Data Index: 6764432 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.9704. Min Act: -0.1700
Data Index: 2320700 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.9391. Min Act: -0.1700
Data Index: 1072548 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.9079. Min Act: -0.1700
Data Index: 4762908 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.9079. Min Act: -0.1700
Data Index: 1072546 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.8766. Min Act: -0.1700
Data Index: 918428 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.8454. Min Act: -0.1700
Data Index: 4340873 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.8141. Min Act: -0.1700
Data Index: 4209932 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.8141. Min Act: -0.1700
Data Index: 1104313 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.8141. Min Act: -0.1700
Data Index: 7663133 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.7829. Min Act: -0.1700
Data Index: 3772665 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.7829. Min Act: -0.1700
Data Index: 1072550 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.7516. Min Act: -0.1700
Data Index: 1188059 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.7516. Min Act: -0.1700
Data Index: 5212993 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1891. Min Range: -5.1891
Max Act: 4.7516. Min Act: -0.1700
Data Index: 6578483 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19