Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2127 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2298. Min Range: -9.2298
Max Act: 9.2298. Min Act: -0.1700
Data Index: 2141355 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2298. Min Range: -9.2298
Max Act: 9.1048. Min Act: -0.1700
Data Index: 3168595 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.9798. Min Act: -0.1700
Data Index: 3491976 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.9798. Min Act: -0.1700
Data Index: 7526170 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.9173. Min Act: -0.1700
Data Index: 1378480 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.9173. Min Act: -0.1700
Data Index: 1557611 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.9173. Min Act: -0.1700
Data Index: 6500498 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7923. Min Act: -0.1700
Data Index: 5064962 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7923. Min Act: -0.1700
Data Index: 7994176 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.8548. Min Act: -0.1700
Data Index: 5590756 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.8548. Min Act: -0.1700
Data Index: 1890425 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.8548. Min Act: -0.1700
Data Index: 8196827 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7923. Min Act: -0.1700
Data Index: 1077971 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 877694 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 2315235 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 5823101 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 3510845 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 4787829 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.7298. Min Act: -0.1700
Data Index: 7445971 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2298. Min Range: -9.2298
Max Act: 8.6673. Min Act: -0.1700
Data Index: 4691405 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19