Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.9267. Min Act: -0.1700
Data Index: 6888359 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2120367 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5993377 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7705. Min Act: -0.1700
Data Index: 1996040 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7705. Min Act: -0.1700
Data Index: 6496850 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 934856 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 8357789 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7421855 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 6633785 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7080. Min Act: -0.1700
Data Index: 7009461 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.6767. Min Act: -0.1700
Data Index: 5486425 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.6455. Min Act: -0.1700
Data Index: 2892616 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.6142. Min Act: -0.1700
Data Index: 8092966 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.6142. Min Act: -0.1700
Data Index: 157340 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.6142. Min Act: -0.1700
Data Index: 6399549 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.5830. Min Act: -0.1700
Data Index: 4212731 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.5830. Min Act: -0.1700
Data Index: 3281525 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.5830. Min Act: -0.1700
Data Index: 7428019 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.5517. Min Act: -0.1700
Data Index: 2561932 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.5517. Min Act: -0.1700
Data Index: 5715374 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19