Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0633. Min Range: -6.0633
Max Act: 6.0633. Min Act: -0.1700
Data Index: 956897 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.6883. Min Act: -0.1700
Data Index: 3763623 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.6570. Min Act: -0.1700
Data Index: 3836805 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8569270 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.3758. Min Act: -0.1700
Data Index: 7957863 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.3445. Min Act: -0.1700
Data Index: 2944424 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.3133. Min Act: -0.1700
Data Index: 393646 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 71057 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 281916 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2508. Min Act: -0.1700
Data Index: 1902722 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2508. Min Act: -0.1700
Data Index: 2929542 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2195. Min Act: -0.1700
Data Index: 5097786 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7607675 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1883. Min Act: -0.1700
Data Index: 609579 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1570. Min Act: -0.1700
Data Index: 3417642 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1570. Min Act: -0.1700
Data Index: 1280638 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1570. Min Act: -0.1700
Data Index: 7322809 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1570. Min Act: -0.1700
Data Index: 5620968 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1258. Min Act: -0.1700
Data Index: 7752095 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0633. Min Range: -6.0633
Max Act: 5.1258. Min Act: -0.1700
Data Index: 7122566 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19