Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.4850. Min Act: -0.1700
Data Index: 6537124 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.4225. Min Act: -0.1700
Data Index: 6556407 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.3600. Min Act: -0.1700
Data Index: 5869487 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2975. Min Act: -0.1700
Data Index: 6537125 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2975. Min Act: -0.1700
Data Index: 4695093 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2975. Min Act: -0.1700
Data Index: 4778656 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.3287. Min Act: -0.1700
Data Index: 274508 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2662. Min Act: -0.1700
Data Index: 4596896 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2662. Min Act: -0.1700
Data Index: 4604655 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2037. Min Act: -0.1700
Data Index: 1527594 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.2350. Min Act: -0.1700
Data Index: 8550919 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1725. Min Act: -0.1700
Data Index: 4647145 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1725. Min Act: -0.1700
Data Index: 2319095 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1725. Min Act: -0.1700
Data Index: 2206797 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1725. Min Act: -0.1700
Data Index: 6809675 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1412. Min Act: -0.1700
Data Index: 3146640 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1412. Min Act: -0.1700
Data Index: 3191906 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1412. Min Act: -0.1700
Data Index: 3263794 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5165121 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4850. Min Range: -5.4850
Max Act: 5.1412. Min Act: -0.1700
Data Index: 1111428 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19