Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.9849. Min Act: -0.1700
Data Index: 3381395 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.9224. Min Act: -0.1700
Data Index: 2648586 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.8599. Min Act: -0.1700
Data Index: 8031240 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.9224. Min Act: -0.1700
Data Index: 2576496 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.8599. Min Act: -0.1700
Data Index: 3381404 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.8599. Min Act: -0.1700
Data Index: 2993232 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.8599. Min Act: -0.1700
Data Index: 8332219 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.8599. Min Act: -0.1700
Data Index: 8182841 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 7392991 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 4779092 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 8332209 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 1639959 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 5652022 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 2516517 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7974. Min Act: -0.1700
Data Index: 3952872 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7349. Min Act: -0.1700
Data Index: 1639966 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7349. Min Act: -0.1700
Data Index: 4473700 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7349. Min Act: -0.1700
Data Index: 6687338 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7349. Min Act: -0.1700
Data Index: 3702974 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9849. Min Range: -6.9849
Max Act: 6.7349. Min Act: -0.1700
Data Index: 2993240 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19