Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.8770. Min Act: -0.1700
Data Index: 4208104 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7988. Min Act: -0.1700
Data Index: 3898474 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7519. Min Act: -0.1700
Data Index: 3305910 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7362. Min Act: -0.1700
Data Index: 4660553 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7362. Min Act: -0.1700
Data Index: 2406903 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7362. Min Act: -0.1700
Data Index: 1783496 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.7362. Min Act: -0.1700
Data Index: 347190 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.6424. Min Act: -0.1700
Data Index: 5749381 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6932638 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.6424. Min Act: -0.1700
Data Index: 3193648 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.6111. Min Act: -0.1700
Data Index: 3423379 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.6111. Min Act: -0.1700
Data Index: 4877801 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5954. Min Act: -0.1700
Data Index: 1485815 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5798. Min Act: -0.1700
Data Index: 744601 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5798. Min Act: -0.1700
Data Index: 6195697 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5798. Min Act: -0.1700
Data Index: 4632069 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5641. Min Act: -0.1700
Data Index: 8527112 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5641. Min Act: -0.1700
Data Index: 3233447 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5641. Min Act: -0.1700
Data Index: 8755605 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8770. Min Range: -3.8770
Max Act: 3.5641. Min Act: -0.1700
Data Index: 1271560 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19