Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4210 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0867. Min Range: -4.0867
Max Act: 4.0867. Min Act: -0.1700
Data Index: 4306112 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.7584. Min Act: -0.1700
Data Index: 3042165 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.6958. Min Act: -0.1700
Data Index: 3940227 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.6489. Min Act: -0.1700
Data Index: 86344 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.6332. Min Act: -0.1700
Data Index: 5743927 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.6489. Min Act: -0.1700
Data Index: 2078896 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.6176. Min Act: -0.1700
Data Index: 7138919 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5863. Min Act: -0.1700
Data Index: 831490 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5706. Min Act: -0.1700
Data Index: 5977727 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5550. Min Act: -0.1700
Data Index: 7412531 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5393. Min Act: -0.1700
Data Index: 830973 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5550. Min Act: -0.1700
Data Index: 3873802 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5550. Min Act: -0.1700
Data Index: 5035336 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5237. Min Act: -0.1700
Data Index: 6730636 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5237. Min Act: -0.1700
Data Index: 6838000 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.4923. Min Act: -0.1700
Data Index: 589542 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5080. Min Act: -0.1700
Data Index: 761776 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.4767. Min Act: -0.1700
Data Index: 5437427 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.4767. Min Act: -0.1700
Data Index: 64472 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0867. Min Range: -4.0867
Max Act: 3.5080. Min Act: -0.1700
Data Index: 1034097 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19