Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.3298. Min Act: -0.1700
Data Index: 7199887 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2984. Min Act: -0.1700
Data Index: 7900286 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2513. Min Act: -0.1700
Data Index: 2218609 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2199. Min Act: -0.1700
Data Index: 6693369 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2199. Min Act: -0.1700
Data Index: 7595909 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2199. Min Act: -0.1700
Data Index: 8583642 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.2041. Min Act: -0.1700
Data Index: 3214988 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1884. Min Act: -0.1700
Data Index: 519590 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 5560105 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 5465710 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 7265726 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1569. Min Act: -0.1700
Data Index: 4538638 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 6332898 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 4024666 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 4337882 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1412. Min Act: -0.1700
Data Index: 5986983 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1727. Min Act: -0.1700
Data Index: 64659 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1412. Min Act: -0.1700
Data Index: 7976411 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1412. Min Act: -0.1700
Data Index: 4637655 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3298. Min Range: -3.3298
Max Act: 3.1569. Min Act: -0.1700
Data Index: 4466357 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19