Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.2265. Min Act: -0.1700
Data Index: 5268723 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.1328. Min Act: -0.1700
Data Index: 7221516 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.0390. Min Act: -0.1700
Data Index: 3388506 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.0390. Min Act: -0.1700
Data Index: 4994803 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2112138 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2265. Min Range: -4.2265
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4492106 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.9452. Min Act: -0.1700
Data Index: 5389044 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.9139. Min Act: -0.1700
Data Index: 6716556 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.9139. Min Act: -0.1700
Data Index: 1703818 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.9139. Min Act: -0.1700
Data Index: 2336091 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8670. Min Act: -0.1700
Data Index: 773653 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8827. Min Act: -0.1700
Data Index: 7304764 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8827. Min Act: -0.1700
Data Index: 2414166 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8827. Min Act: -0.1700
Data Index: 3338797 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8827. Min Act: -0.1700
Data Index: 3961318 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8827. Min Act: -0.1700
Data Index: 4981050 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8670. Min Act: -0.1700
Data Index: 617722 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8670. Min Act: -0.1700
Data Index: 2455518 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8670. Min Act: -0.1700
Data Index: 7295596 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2265. Min Range: -4.2265
Max Act: 3.8358. Min Act: -0.1700
Data Index: 3171737 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19