Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0716. Min Range: -4.0716
Max Act: 4.0716. Min Act: -0.1700
Data Index: 3774626 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0716. Min Range: -4.0716
Max Act: 4.0716. Min Act: -0.1700
Data Index: 6673041 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0716. Min Range: -4.0716
Max Act: 4.0403. Min Act: -0.1700
Data Index: 6020064 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9778. Min Act: -0.1700
Data Index: 3102014 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9465. Min Act: -0.1700
Data Index: 4574335 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9465. Min Act: -0.1700
Data Index: 8015875 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9465. Min Act: -0.1700
Data Index: 826825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9465. Min Act: -0.1700
Data Index: 2166961 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 6755544 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 5302517 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 2395357 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 67366 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9465. Min Act: -0.1700
Data Index: 1398231 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 4332108 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 6985032 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.9152. Min Act: -0.1700
Data Index: 6567203 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.8840. Min Act: -0.1700
Data Index: 2994409 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.8527. Min Act: -0.1700
Data Index: 5302514 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.8527. Min Act: -0.1700
Data Index: 2100874 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0716. Min Range: -4.0716
Max Act: 3.8840. Min Act: -0.1700
Data Index: 5445142 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19