Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1350. Min Range: -8.1350
Max Act: 8.1350. Min Act: -0.1700
Data Index: 5445915 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1350. Min Range: -8.1350
Max Act: 8.1037. Min Act: -0.1700
Data Index: 6128182 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1350. Min Range: -8.1350
Max Act: 8.1350. Min Act: -0.1700
Data Index: 4164586 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1350. Min Range: -8.1350
Max Act: 8.0412. Min Act: -0.1700
Data Index: 8614323 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1350. Min Range: -8.1350
Max Act: 8.0412. Min Act: -0.1700
Data Index: 3915401 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.9787. Min Act: -0.1700
Data Index: 2551772 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 2992408 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 8123952 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8537. Min Act: -0.1700
Data Index: 2792205 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 5657413 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.9162. Min Act: -0.1700
Data Index: 3967568 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 8381954 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 2290491 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 1139482 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 6621638 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8537. Min Act: -0.1700
Data Index: 4871574 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8537. Min Act: -0.1700
Data Index: 8044001 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8850. Min Act: -0.1700
Data Index: 7044559 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8225. Min Act: -0.1700
Data Index: 2921267 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1350. Min Range: -8.1350
Max Act: 7.8225. Min Act: -0.1700
Data Index: 6706853 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19