Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.9075. Min Act: -0.1700
Data Index: 312386 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.8762. Min Act: -0.1700
Data Index: 6710507 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 4068183 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1876671 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 651800 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7512. Min Act: -0.1700
Data Index: 2180901 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7512. Min Act: -0.1700
Data Index: 1056342 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7512. Min Act: -0.1700
Data Index: 3657063 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7200. Min Act: -0.1700
Data Index: 7662858 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 56704 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 1950513 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6262. Min Act: -0.1700
Data Index: 8465278 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 7451789 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6575. Min Act: -0.1700
Data Index: 2556775 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6575. Min Act: -0.1700
Data Index: 5611022 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6262. Min Act: -0.1700
Data Index: 8169929 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6262. Min Act: -0.1700
Data Index: 1211347 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6262. Min Act: -0.1700
Data Index: 556341 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6262. Min Act: -0.1700
Data Index: 4309325 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.5950. Min Act: -0.1700
Data Index: 1967378 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19