Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5921 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1391. Min Range: -7.1391
Max Act: 7.1391. Min Act: -0.1700
Data Index: 8006705 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1391. Min Range: -7.1391
Max Act: 7.1079. Min Act: -0.1700
Data Index: 6010130 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.9829. Min Act: -0.1700
Data Index: 1102655 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.9204. Min Act: -0.1700
Data Index: 5994803 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.8266. Min Act: -0.1700
Data Index: 4615647 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.7954. Min Act: -0.1700
Data Index: 5930992 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.7329. Min Act: -0.1700
Data Index: 1411941 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.7329. Min Act: -0.1700
Data Index: 500586 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.6704. Min Act: -0.1700
Data Index: 1832498 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.6704. Min Act: -0.1700
Data Index: 2379011 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8613132 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.6704. Min Act: -0.1700
Data Index: 3181256 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.6079. Min Act: -0.1700
Data Index: 5489235 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5766. Min Act: -0.1700
Data Index: 8490221 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5766. Min Act: -0.1699
Data Index: 6555131 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5766. Min Act: -0.1700
Data Index: 2777323 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5141. Min Act: -0.1700
Data Index: 4215905 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5141. Min Act: -0.1700
Data Index: 5222029 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5141. Min Act: -0.1700
Data Index: 4745803 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1391. Min Range: -7.1391
Max Act: 6.5141. Min Act: -0.1700
Data Index: 541310 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19