Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 519 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.6079. Min Act: -0.1700
Data Index: 583494 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.2329. Min Act: -0.1700
Data Index: 3528333 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.2329. Min Act: -0.1700
Data Index: 5688797 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.1704. Min Act: -0.1700
Data Index: 5483368 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.0454. Min Act: -0.1700
Data Index: 4717784 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6079. Min Range: -8.6079
Max Act: 8.0141. Min Act: -0.1700
Data Index: 3948822 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.8579. Min Act: -0.1700
Data Index: 3729500 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.8266. Min Act: -0.1700
Data Index: 3205419 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.7641. Min Act: -0.1700
Data Index: 1890108 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.7641. Min Act: -0.1700
Data Index: 3539543 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.7329. Min Act: -0.1700
Data Index: 3581945 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.7641. Min Act: -0.1700
Data Index: 1771107 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.7016. Min Act: -0.1700
Data Index: 7074779 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.6391. Min Act: -0.1700
Data Index: 8334879 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.6079. Min Act: -0.1700
Data Index: 1517633 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.6079. Min Act: -0.1700
Data Index: 5735422 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.5766. Min Act: -0.1700
Data Index: 1926355 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.5766. Min Act: -0.1700
Data Index: 4450385 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.5454. Min Act: -0.1700
Data Index: 3899869 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6079. Min Range: -8.6079
Max Act: 7.5141. Min Act: -0.1700
Data Index: 5558432 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19