Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.2807. Min Act: -0.1700
Data Index: 105034 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0619. Min Act: -0.1700
Data Index: 1882810 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6159870 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0307. Min Act: -0.1700
Data Index: 8739150 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6328438 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0307. Min Act: -0.1700
Data Index: 3641492 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2807. Min Range: -5.2807
Max Act: 5.0307. Min Act: -0.1700
Data Index: 6314817 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9682. Min Act: -0.1700
Data Index: 772798 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9682. Min Act: -0.1700
Data Index: 8302892 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9682. Min Act: -0.1700
Data Index: 5152849 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9369. Min Act: -0.1700
Data Index: 4390371 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9369. Min Act: -0.1700
Data Index: 2555789 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9369. Min Act: -0.1700
Data Index: 678691 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9057. Min Act: -0.1700
Data Index: 6261379 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9057. Min Act: -0.1700
Data Index: 8006920 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9057. Min Act: -0.1700
Data Index: 7903521 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.8744. Min Act: -0.1700
Data Index: 3419837 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.8744. Min Act: -0.1700
Data Index: 8602473 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.9057. Min Act: -0.1700
Data Index: 129934 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2807. Min Range: -5.2807
Max Act: 4.8744. Min Act: -0.1700
Data Index: 2306064 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19