Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5603 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0326. Min Range: -6.0326
Max Act: 6.0326. Min Act: -0.1700
Data Index: 6603457 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.7826. Min Act: -0.1700
Data Index: 2834670 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6576. Min Act: -0.1700
Data Index: 2189325 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6074868 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5951. Min Act: -0.1700
Data Index: 8332717 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5638. Min Act: -0.1700
Data Index: 8705399 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5638. Min Act: -0.1700
Data Index: 4679040 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 5125029 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 754797 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 3093319 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5638. Min Act: -0.1700
Data Index: 300613 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 3198378 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 4102551 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5013. Min Act: -0.1700
Data Index: 7231957 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5013. Min Act: -0.1700
Data Index: 5108828 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5013. Min Act: -0.1700
Data Index: 7499852 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.4701. Min Act: -0.1700
Data Index: 6529100 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5013. Min Act: -0.1700
Data Index: 4958162 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5013. Min Act: -0.1700
Data Index: 2940942 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.5326. Min Act: -0.1700
Data Index: 8373427 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19