Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.8718. Min Act: -0.1700
Data Index: 3159937 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3159932 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.3405. Min Act: -0.1700
Data Index: 273003 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.3093. Min Act: -0.1700
Data Index: 7542822 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.3405. Min Act: -0.1700
Data Index: 7700537 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.1530. Min Act: -0.1700
Data Index: 2403046 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8718. Min Range: -6.8718
Max Act: 6.0593. Min Act: -0.1700
Data Index: 5594839 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8718. Min Act: -0.1700
Data Index: 8345426 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8718. Min Act: -0.1700
Data Index: 5457778 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8405. Min Act: -0.1700
Data Index: 179865 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8093. Min Act: -0.1700
Data Index: 3871214 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.7780. Min Act: -0.1700
Data Index: 3159931 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8405. Min Act: -0.1700
Data Index: 4098757 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.8093. Min Act: -0.1700
Data Index: 3136596 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.7780. Min Act: -0.1700
Data Index: 382506 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.7468. Min Act: -0.1700
Data Index: 984227 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.7468. Min Act: -0.1700
Data Index: 8667926 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.7468. Min Act: -0.1700
Data Index: 1509356 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.6843. Min Act: -0.1700
Data Index: 7859762 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8718. Min Range: -6.8718
Max Act: 5.6843. Min Act: -0.1700
Data Index: 5870362 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19