Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5517 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1828. Min Range: -6.1828
Max Act: 6.1828. Min Act: -0.1700
Data Index: 3666566 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1828. Min Range: -6.1828
Max Act: 6.1828. Min Act: -0.1700
Data Index: 726462 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1828. Min Range: -6.1828
Max Act: 6.1203. Min Act: -0.1700
Data Index: 5995829 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.8078. Min Act: -0.1700
Data Index: 4230319 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.7453. Min Act: -0.1700
Data Index: 4592897 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.7140. Min Act: -0.1700
Data Index: 5893283 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.7140. Min Act: -0.1700
Data Index: 6275175 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.7140. Min Act: -0.1700
Data Index: 6083236 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6938484 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6515. Min Act: -0.1700
Data Index: 1618247 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6515. Min Act: -0.1700
Data Index: 4678938 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6203. Min Act: -0.1700
Data Index: 1946700 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6203. Min Act: -0.1700
Data Index: 3021998 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5890. Min Act: -0.1700
Data Index: 375173 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5890. Min Act: -0.1700
Data Index: 5708199 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5890. Min Act: -0.1700
Data Index: 1195855 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5890. Min Act: -0.1700
Data Index: 4698256 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5261807 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5578. Min Act: -0.1700
Data Index: 8633338 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1828. Min Range: -6.1828
Max Act: 5.5578. Min Act: -0.1700
Data Index: 6264664 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19