Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.8071. Min Act: -0.1700
Data Index: 5958797 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7446. Min Act: -0.1700
Data Index: 4860018 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3527892 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7133. Min Act: -0.1700
Data Index: 849141 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7133. Min Act: -0.1700
Data Index: 4125364 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6821. Min Act: -0.1700
Data Index: 4470595 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7133. Min Act: -0.1700
Data Index: 6514684 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6821. Min Act: -0.1700
Data Index: 3530931 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3723710 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6821. Min Act: -0.1700
Data Index: 1493254 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6821. Min Act: -0.1700
Data Index: 1528515 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 811549 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3495444 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3475245 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 558294 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3417842 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6821. Min Act: -0.1700
Data Index: 7684721 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6508. Min Act: -0.1700
Data Index: 7386122 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1681425 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8071. Min Range: -5.8071
Max Act: 5.5883. Min Act: -0.1700
Data Index: 2339043 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19