Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 697001 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1331. Min Act: -0.1700
Data Index: 8639226 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 8537885 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8502205 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8171785 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 6439027 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 4543900 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 1498780 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 6473495 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 3576104 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 8808640 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 3130890 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 6548374 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9456. Min Act: -0.1700
Data Index: 27437 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 7197533 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 2163328 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 6515310 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8831. Min Act: -0.1700
Data Index: 6082751 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 4011451 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8831. Min Act: -0.1700
Data Index: 2705680 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19