Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0308. Min Range: -6.0308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 3653594 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.9683. Min Act: -0.1700
Data Index: 6999548 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.9371. Min Act: -0.1700
Data Index: 6413609 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8433. Min Act: -0.1700
Data Index: 8741242 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8433. Min Act: -0.1700
Data Index: 1253442 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8121. Min Act: -0.1700
Data Index: 7578429 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7496. Min Act: -0.1700
Data Index: 5616333 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7496. Min Act: -0.1700
Data Index: 3479319 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7808. Min Act: -0.1700
Data Index: 1925054 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7496. Min Act: -0.1700
Data Index: 8027663 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7183. Min Act: -0.1700
Data Index: 4578905 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7183. Min Act: -0.1700
Data Index: 808890 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 7488944 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 7328806 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 3400046 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 7428289 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5270607 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 2999260 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 3141772 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 5386184 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19