Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.2375. Min Act: -0.1700
Data Index: 2138653 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1750. Min Act: -0.1700
Data Index: 190699 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1750. Min Act: -0.1700
Data Index: 7910981 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1750. Min Act: -0.1700
Data Index: 940861 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1750. Min Act: -0.1700
Data Index: 7862311 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1750. Min Act: -0.1700
Data Index: 7885095 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1437. Min Act: -0.1700
Data Index: 8306678 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1437. Min Act: -0.1700
Data Index: 5805401 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.1125. Min Act: -0.1700
Data Index: 5392475 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0812. Min Act: -0.1700
Data Index: 4852435 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0500. Min Act: -0.1700
Data Index: 7298090 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0500. Min Act: -0.1700
Data Index: 2390350 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0187. Min Act: -0.1700
Data Index: 7635742 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0187. Min Act: -0.1700
Data Index: 1753728 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0500. Min Act: -0.1700
Data Index: 350895 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4167827 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4815223 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2375. Min Range: -5.2375
Max Act: 5.0187. Min Act: -0.1700
Data Index: 784633 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2375. Min Range: -5.2375
Max Act: 4.9875. Min Act: -0.1700
Data Index: 7034239 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2375. Min Range: -5.2375
Max Act: 4.9562. Min Act: -0.1700
Data Index: 2131587 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19