Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.5150. Min Act: -0.1700
Data Index: 7770181 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.4525. Min Act: -0.1700
Data Index: 3613909 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.2650. Min Act: -0.1700
Data Index: 4062507 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.2025. Min Act: -0.1700
Data Index: 3459426 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.2025. Min Act: -0.1700
Data Index: 3381797 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.1400. Min Act: -0.1700
Data Index: 2226160 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 3312901 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 3381803 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 4106486 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 3312908 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5150. Min Range: -9.5150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 6366918 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 1672209 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 3737278 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 3922259 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 1553460 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 3922260 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.9525. Min Act: -0.1700
Data Index: 7988561 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.8900. Min Act: -0.1700
Data Index: 6826253 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.8900. Min Act: -0.1700
Data Index: 8439569 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5150. Min Range: -9.5150
Max Act: 8.8900. Min Act: -0.1700
Data Index: 6366921 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19