Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.8937. Min Act: -0.1700
Data Index: 1378863 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.7373. Min Act: -0.1700
Data Index: 5702417 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.7373. Min Act: -0.1700
Data Index: 7236488 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.7060. Min Act: -0.1700
Data Index: 5351423 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6904. Min Act: -0.1700
Data Index: 2402773 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.7060. Min Act: -0.1700
Data Index: 6167008 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.7216. Min Act: -0.1700
Data Index: 2221500 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6747. Min Act: -0.1700
Data Index: 69634 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6904. Min Act: -0.1700
Data Index: 6954645 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6747. Min Act: -0.1700
Data Index: 1174189 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6747. Min Act: -0.1700
Data Index: 802619 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6434. Min Act: -0.1700
Data Index: 7155322 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6591. Min Act: -0.1700
Data Index: 5872573 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6591. Min Act: -0.1700
Data Index: 218778 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6591. Min Act: -0.1700
Data Index: 7946252 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6591. Min Act: -0.1700
Data Index: 6958312 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6591. Min Act: -0.1700
Data Index: 1461627 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6434. Min Act: -0.1700
Data Index: 5112907 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6278. Min Act: -0.1700
Data Index: 792671 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8937. Min Range: -3.8937
Max Act: 3.6121. Min Act: -0.1700
Data Index: 2659107 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19