Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4831 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3410099 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.7025. Min Act: -0.1700
Data Index: 3089731 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.6400. Min Act: -0.1699
Data Index: 5930358 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5775. Min Act: -0.1700
Data Index: 5708236 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.6088. Min Act: -0.1698
Data Index: 2104253 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.6088. Min Act: -0.1700
Data Index: 4760413 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5775. Min Act: -0.1700
Data Index: 5934340 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5775. Min Act: -0.1700
Data Index: 4263101 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5463. Min Act: -0.1700
Data Index: 1609764 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5463. Min Act: -0.1700
Data Index: 306411 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 3272161 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 2447812 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 8396598 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5463. Min Act: -0.1700
Data Index: 313806 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 5480308 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.4838. Min Act: -0.1700
Data Index: 260126 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.4838. Min Act: -0.1700
Data Index: 4844359 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 2051033 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5150. Min Act: -0.1700
Data Index: 4059380 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.4838. Min Act: -0.1700
Data Index: 1236605 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19