Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1392. Min Range: -6.1392
Max Act: 6.1392. Min Act: -0.1700
Data Index: 8798239 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1392. Min Range: -6.1392
Max Act: 6.0767. Min Act: -0.1700
Data Index: 7600948 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1392. Min Range: -6.1392
Max Act: 6.0142. Min Act: -0.1700
Data Index: 5208858 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.9829. Min Act: -0.1700
Data Index: 1569475 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.9517. Min Act: -0.1700
Data Index: 3281932 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.8579. Min Act: -0.1700
Data Index: 8482723 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.8579. Min Act: -0.1700
Data Index: 190396 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.8267. Min Act: -0.1700
Data Index: 756434 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.8267. Min Act: -0.1700
Data Index: 6806376 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7954. Min Act: -0.1700
Data Index: 1066218 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7954. Min Act: -0.1700
Data Index: 197399 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7954. Min Act: -0.1700
Data Index: 4395811 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7642. Min Act: -0.1700
Data Index: 8342114 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7642. Min Act: -0.1700
Data Index: 7659842 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7642. Min Act: -0.1700
Data Index: 3804272 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7329. Min Act: -0.1700
Data Index: 1000791 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7017. Min Act: -0.1700
Data Index: 4009989 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7017. Min Act: -0.1700
Data Index: 6183114 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.7017. Min Act: -0.1700
Data Index: 1139975 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1392. Min Range: -6.1392
Max Act: 5.6704. Min Act: -0.1700
Data Index: 1513308 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19