Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7575. Min Act: -0.1700
Data Index: 5625699 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7888. Min Act: -0.1700
Data Index: 3749775 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7575. Min Act: -0.1700
Data Index: 2727820 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.7263. Min Act: -0.1700
Data Index: 4326159 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6950. Min Act: -0.1700
Data Index: 1017749 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6950. Min Act: -0.1700
Data Index: 5377033 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6637. Min Act: -0.1700
Data Index: 4605264 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6637. Min Act: -0.1700
Data Index: 6667861 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6011. Min Act: -0.1700
Data Index: 7346295 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.6011. Min Act: -0.1700
Data Index: 6260874 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5854. Min Act: -0.1700
Data Index: 7674127 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5854. Min Act: -0.1700
Data Index: 616599 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5698. Min Act: -0.1700
Data Index: 4326155 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5541. Min Act: -0.1700
Data Index: 2295175 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5228. Min Act: -0.1700
Data Index: 8530929 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5072. Min Act: -0.1700
Data Index: 8443337 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5228. Min Act: -0.1700
Data Index: 8381770 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5228. Min Act: -0.1700
Data Index: 363665 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5228. Min Act: -0.1700
Data Index: 8787869 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7888. Min Range: -3.7888
Max Act: 3.5072. Min Act: -0.1700
Data Index: 3610213 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19