Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6391. Min Range: -10.6391
Max Act: 10.6391. Min Act: -0.1700
Data Index: 3771271 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6391. Min Range: -10.6391
Max Act: 10.3266. Min Act: -0.1700
Data Index: 7629329 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6391. Min Range: -10.6391
Max Act: 10.0141. Min Act: -0.1700
Data Index: 1836014 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.9516. Min Act: -0.1700
Data Index: 2130463 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7641. Min Act: -0.1700
Data Index: 4692007 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7016. Min Act: -0.1700
Data Index: 5567461 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7641. Min Act: -0.1700
Data Index: 595751 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.8266. Min Act: -0.1700
Data Index: 6492985 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7641. Min Act: -0.1700
Data Index: 6496283 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7016. Min Act: -0.1700
Data Index: 7763268 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.7016. Min Act: -0.1700
Data Index: 4667196 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.6391. Min Act: -0.1700
Data Index: 2076545 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.6391. Min Act: -0.1700
Data Index: 886628 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5766. Min Act: -0.1700
Data Index: 7862738 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5141. Min Act: -0.1700
Data Index: 3620280 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5766. Min Act: -0.1700
Data Index: 380973 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5141. Min Act: -0.1700
Data Index: 3866550 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5141. Min Act: -0.1700
Data Index: 1516481 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.5141. Min Act: -0.1700
Data Index: 4907956 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6391. Min Range: -10.6391
Max Act: 9.4516. Min Act: -0.1700
Data Index: 1496588 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19