Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4707 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6908509 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.8454. Min Act: -0.1700
Data Index: 2010050 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.7204. Min Act: -0.1700
Data Index: 6311005 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.6267. Min Act: -0.1700
Data Index: 6064696 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.6267. Min Act: -0.1700
Data Index: 7181522 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5954. Min Act: -0.1700
Data Index: 4682888 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5954. Min Act: -0.1700
Data Index: 5480965 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5329. Min Act: -0.1700
Data Index: 2114576 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5642. Min Act: -0.1700
Data Index: 7490614 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4704. Min Act: -0.1700
Data Index: 7871 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 5480964 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.5017. Min Act: -0.1700
Data Index: 26660 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4704. Min Act: -0.1700
Data Index: 7291305 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4704. Min Act: -0.1700
Data Index: 7374679 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 8076562 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 6547478 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 5471247 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4704. Min Act: -0.1700
Data Index: 2265571 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 875324 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8767. Min Range: -4.8767
Max Act: 4.4392. Min Act: -0.1700
Data Index: 4808672 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19