Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0999. Min Range: -5.0999
Max Act: 5.0999. Min Act: -0.1700
Data Index: 7140576 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0999. Min Range: -5.0999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 1190736 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0999. Min Range: -5.0999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 3425806 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.8499. Min Act: -0.1700
Data Index: 8516766 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.8499. Min Act: -0.1700
Data Index: 8217309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7874. Min Act: -0.1700
Data Index: 4046918 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7874. Min Act: -0.1700
Data Index: 7445103 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7561. Min Act: -0.1700
Data Index: 312815 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7874. Min Act: -0.1700
Data Index: 2527563 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7561. Min Act: -0.1700
Data Index: 4155803 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7249. Min Act: -0.1700
Data Index: 3629870 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7249. Min Act: -0.1700
Data Index: 4129772 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7249. Min Act: -0.1700
Data Index: 6531495 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.7249. Min Act: -0.1700
Data Index: 422754 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 5482827 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 8537282 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 8448839 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 6780604 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 629594 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0999. Min Range: -5.0999
Max Act: 4.5686. Min Act: -0.1700
Data Index: 3943239 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19