Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3959 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.5331. Min Act: -0.1700
Data Index: 7000322 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.4081. Min Act: -0.1700
Data Index: 470309 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.0644. Min Act: -0.1700
Data Index: 8670008 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.0956. Min Act: -0.1700
Data Index: 6095605 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.0019. Min Act: -0.1700
Data Index: 3633095 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5331. Min Range: -8.5331
Max Act: 8.0019. Min Act: -0.1700
Data Index: 1872497 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.9706. Min Act: -0.1700
Data Index: 5775861 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.9706. Min Act: -0.1700
Data Index: 591401 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.9394. Min Act: -0.1700
Data Index: 790105 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.9394. Min Act: -0.1700
Data Index: 4964472 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8769. Min Act: -0.1700
Data Index: 5895906 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.9081. Min Act: -0.1700
Data Index: 1304162 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8769. Min Act: -0.1700
Data Index: 3226230 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8456. Min Act: -0.1700
Data Index: 1011677 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8456. Min Act: -0.1700
Data Index: 5798134 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8769. Min Act: -0.1700
Data Index: 168787 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8769. Min Act: -0.1700
Data Index: 5707340 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.8144. Min Act: -0.1700
Data Index: 6078300 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.7831. Min Act: -0.1700
Data Index: 5130672 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5331. Min Range: -8.5331
Max Act: 7.7519. Min Act: -0.1700
Data Index: 7701480 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19