Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1552 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.8850. Min Act: -0.1700
Data Index: 6581102 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.3225. Min Act: -0.1700
Data Index: 396834 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.2600. Min Act: -0.1700
Data Index: 5993938 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.1975. Min Act: -0.1700
Data Index: 2254620 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.1975. Min Act: -0.1700
Data Index: 1584825 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 1605357 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 7849123 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 766808 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 5781388 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 2389133 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.0100. Min Act: -0.1700
Data Index: 5700118 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.0100. Min Act: -0.1700
Data Index: 8708803 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8850. Min Range: -8.8850
Max Act: 8.0100. Min Act: -0.1700
Data Index: 2933271 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.9475. Min Act: -0.1700
Data Index: 1401331 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.9475. Min Act: -0.1700
Data Index: 4854873 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.9475. Min Act: -0.1700
Data Index: 7342944 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.8850. Min Act: -0.1700
Data Index: 6930082 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.8850. Min Act: -0.1700
Data Index: 2725768 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.8850. Min Act: -0.1700
Data Index: 3927136 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8850. Min Range: -8.8850
Max Act: 7.8850. Min Act: -0.1700
Data Index: 5437214 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19