Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0223. Min Range: -6.0223
Max Act: 6.0223. Min Act: -0.1700
Data Index: 8237785 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3198612 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.9285. Min Act: -0.1700
Data Index: 2145795 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.9598. Min Act: -0.1700
Data Index: 5688936 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8660. Min Act: -0.1700
Data Index: 1486437 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8348. Min Act: -0.1700
Data Index: 8468982 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8348. Min Act: -0.1700
Data Index: 7052829 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8035. Min Act: -0.1700
Data Index: 3510083 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8035. Min Act: -0.1700
Data Index: 2756270 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8035. Min Act: -0.1700
Data Index: 7110205 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.8035. Min Act: -0.1700
Data Index: 3837404 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7723. Min Act: -0.1700
Data Index: 6258534 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3955431 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7410. Min Act: -0.1700
Data Index: 7263988 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7098. Min Act: -0.1700
Data Index: 1821792 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7098. Min Act: -0.1700
Data Index: 3256638 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7098. Min Act: -0.1700
Data Index: 750132 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7410. Min Act: -0.1700
Data Index: 5015715 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.7098. Min Act: -0.1700
Data Index: 1105462 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0223. Min Range: -6.0223
Max Act: 5.6473. Min Act: -0.1700
Data Index: 2194225 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19