Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 586 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.6266. Min Act: -0.1700
Data Index: 7107340 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.6266. Min Act: -0.1700
Data Index: 7035762 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.5016. Min Act: -0.1700
Data Index: 4621423 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.5016. Min Act: -0.1700
Data Index: 8545854 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.5016. Min Act: -0.1700
Data Index: 5453608 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.3766. Min Act: -0.1700
Data Index: 3035670 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.3766. Min Act: -0.1700
Data Index: 2409982 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.3766. Min Act: -0.1700
Data Index: 3335743 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.3141. Min Act: -0.1700
Data Index: 1157720 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.2516. Min Act: -0.1700
Data Index: 323235 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.2516. Min Act: -0.1700
Data Index: 3232079 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1891. Min Act: -0.1700
Data Index: 6685516 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1266. Min Act: -0.1700
Data Index: 6154224 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1266. Min Act: -0.1700
Data Index: 6406517 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1266. Min Act: -0.1700
Data Index: 5395545 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1266. Min Act: -0.1700
Data Index: 1775803 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.0641. Min Act: -0.1700
Data Index: 3361951 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.1266. Min Act: -0.1700
Data Index: 7142110 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.0641. Min Act: -0.1700
Data Index: 7994455 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6266. Min Range: -9.6266
Max Act: 9.0016. Min Act: -0.1700
Data Index: 5083902 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19