Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.6794. Min Act: -0.1700
Data Index: 8479065 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.4919. Min Act: -0.1700
Data Index: 845487 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.3044. Min Act: -0.1700
Data Index: 898865 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.2731. Min Act: -0.1700
Data Index: 298829 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.2419. Min Act: -0.1700
Data Index: 699122 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.2106. Min Act: -0.1700
Data Index: 8065267 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.2106. Min Act: -0.1700
Data Index: 1217010 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1794. Min Act: -0.1700
Data Index: 907372 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1794. Min Act: -0.1700
Data Index: 433009 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1794. Min Act: -0.1700
Data Index: 956296 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1481. Min Act: -0.1700
Data Index: 5798928 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1169. Min Act: -0.1700
Data Index: 2280558 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1246402 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0856. Min Act: -0.1700
Data Index: 6025322 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0544. Min Act: -0.1700
Data Index: 3474412 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0856. Min Act: -0.1700
Data Index: 2175080 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0856. Min Act: -0.1700
Data Index: 2514575 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0856. Min Act: -0.1700
Data Index: 5946911 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1039339 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6794. Min Range: -6.6794
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1478775 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19