Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4839 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.4477. Min Act: -0.1700
Data Index: 428744 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.4477. Min Act: -0.1700
Data Index: 2486317 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.4477. Min Act: -0.1700
Data Index: 5174970 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.4165. Min Act: -0.1700
Data Index: 3488424 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.4165. Min Act: -0.1700
Data Index: 4084773 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3852. Min Act: -0.1700
Data Index: 2423971 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3540. Min Act: -0.1700
Data Index: 2537876 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3227. Min Act: -0.1700
Data Index: 992014 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3227. Min Act: -0.1700
Data Index: 4266099 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3227. Min Act: -0.1700
Data Index: 5556656 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3540. Min Act: -0.1700
Data Index: 5694552 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3227. Min Act: -0.1700
Data Index: 5335038 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2602. Min Act: -0.1700
Data Index: 8673842 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 5147350 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 3740913 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 2486313 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 2486314 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 6682507 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.2915. Min Act: -0.1700
Data Index: 297782 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4477. Min Range: -5.4477
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3330068 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19