Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7710. Min Act: -0.1700
Data Index: 6060620 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7397. Min Act: -0.1700
Data Index: 3942267 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7710. Min Act: -0.1700
Data Index: 3942257 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7084. Min Act: -0.1700
Data Index: 8670237 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7084. Min Act: -0.1700
Data Index: 582301 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.7084. Min Act: -0.1700
Data Index: 1238850 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6458. Min Act: -0.1700
Data Index: 7348943 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6458. Min Act: -0.1700
Data Index: 8011435 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6771. Min Act: -0.1700
Data Index: 5841402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6458. Min Act: -0.1700
Data Index: 6842672 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1037113 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6145. Min Act: -0.1700
Data Index: 8680122 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5832. Min Act: -0.1700
Data Index: 3656998 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6458. Min Act: -0.1700
Data Index: 5898336 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.6145. Min Act: -0.1700
Data Index: 3126851 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5832. Min Act: -0.1700
Data Index: 635589 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5832. Min Act: -0.1700
Data Index: 3336865 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5832. Min Act: -0.1700
Data Index: 4250732 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5676. Min Act: -0.1700
Data Index: 4268771 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7710. Min Range: -3.7710
Max Act: 3.5832. Min Act: -0.1700
Data Index: 5553269 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19