Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4380 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.4850. Min Act: -0.1700
Data Index: 820653 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.3600. Min Act: -0.1700
Data Index: 6348695 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.2975. Min Act: -0.1700
Data Index: 86508 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.1100. Min Act: -0.1698
Data Index: 4324759 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.0475. Min Act: -0.1699
Data Index: 7679800 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4850. Min Range: -9.4850
Max Act: 9.0475. Min Act: -0.1700
Data Index: 1626006 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.9850. Min Act: -0.1700
Data Index: 473419 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.9850. Min Act: -0.1700
Data Index: 5260666 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.9850. Min Act: -0.1700
Data Index: 5532038 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.9225. Min Act: -0.1700
Data Index: 1425980 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.9225. Min Act: -0.1700
Data Index: 8444211 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 6364646 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 7429594 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 2866987 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 3713108 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 4024241 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 7962707 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7975. Min Act: -0.1700
Data Index: 265033 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7350. Min Act: -0.1700
Data Index: 1913998 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4850. Min Range: -9.4850
Max Act: 8.7350. Min Act: -0.1700
Data Index: 3341226 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19