Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2588. Min Range: -8.2588
Max Act: 8.2588. Min Act: -0.1700
Data Index: 5779398 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2588. Min Range: -8.2588
Max Act: 8.1338. Min Act: -0.1700
Data Index: 231069 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2588. Min Range: -8.2588
Max Act: 8.1338. Min Act: -0.1700
Data Index: 7126819 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.9463. Min Act: -0.1700
Data Index: 7909538 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.9463. Min Act: -0.1700
Data Index: 4673684 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.8213. Min Act: -0.1700
Data Index: 1060978 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.7588. Min Act: -0.1700
Data Index: 1109200 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.6650. Min Act: -0.1700
Data Index: 4492853 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.6650. Min Act: -0.1700
Data Index: 1772487 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.6650. Min Act: -0.1700
Data Index: 3206598 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.6025. Min Act: -0.1700
Data Index: 6671494 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.6025. Min Act: -0.1700
Data Index: 8641030 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.5400. Min Act: -0.1700
Data Index: 5419091 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.4775. Min Act: -0.1700
Data Index: 5849919 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.3838. Min Act: -0.1700
Data Index: 337475 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.4150. Min Act: -0.1700
Data Index: 2780847 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.3525. Min Act: -0.1700
Data Index: 4394673 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.3525. Min Act: -0.1700
Data Index: 7826604 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.3525. Min Act: -0.1700
Data Index: 5124891 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2588. Min Range: -8.2588
Max Act: 7.2900. Min Act: -0.1700
Data Index: 1427616 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19