Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1672 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2266. Min Range: -8.2266
Max Act: 8.2266. Min Act: -0.1700
Data Index: 5456427 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.9766. Min Act: -0.1700
Data Index: 3550719 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.9141. Min Act: -0.1700
Data Index: 1285604 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.7266. Min Act: -0.1700
Data Index: 7035238 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.7579. Min Act: -0.1700
Data Index: 7602019 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.7579. Min Act: -0.1700
Data Index: 499601 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.7266. Min Act: -0.1700
Data Index: 4551410 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6641. Min Act: -0.1700
Data Index: 7950903 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6641. Min Act: -0.1700
Data Index: 671628 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6641. Min Act: -0.1700
Data Index: 4973560 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6329. Min Act: -0.1700
Data Index: 7641244 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6329. Min Act: -0.1700
Data Index: 3777399 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.6016. Min Act: -0.1700
Data Index: 5048840 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5704. Min Act: -0.1700
Data Index: 586241 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5704. Min Act: -0.1700
Data Index: 6606262 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5704. Min Act: -0.1700
Data Index: 6262259 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5704. Min Act: -0.1700
Data Index: 4098072 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5391. Min Act: -0.1700
Data Index: 5288059 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5391. Min Act: -0.1700
Data Index: 6354443 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2266. Min Range: -8.2266
Max Act: 7.5391. Min Act: -0.1700
Data Index: 5964156 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19