Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.2679. Min Act: -0.1700
Data Index: 982219 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.2054. Min Act: -0.1700
Data Index: 6477447 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1742. Min Act: -0.1700
Data Index: 968046 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6935533 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1742. Min Act: -0.1700
Data Index: 8170345 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1429. Min Act: -0.1700
Data Index: 6477449 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 8532426 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 8670220 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 2944787 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 7854648 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 7196782 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 5110029 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.1116. Min Act: -0.1700
Data Index: 481254 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0804. Min Act: -0.1700
Data Index: 1775155 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0804. Min Act: -0.1700
Data Index: 7177250 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0804. Min Act: -0.1700
Data Index: 2013516 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0491. Min Act: -0.1700
Data Index: 3905435 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0804. Min Act: -0.1700
Data Index: 677817 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0491. Min Act: -0.1700
Data Index: 3794752 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2679. Min Range: -4.2679
Max Act: 4.0491. Min Act: -0.1700
Data Index: 5412647 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19