Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5731 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.8278. Min Act: -0.1700
Data Index: 5023550 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.7341. Min Act: -0.1700
Data Index: 3864320 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.6716. Min Act: -0.1700
Data Index: 1797628 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.5778. Min Act: -0.1700
Data Index: 1451149 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.5466. Min Act: -0.1700
Data Index: 3721250 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.5153. Min Act: -0.1700
Data Index: 1280831 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4841. Min Act: -0.1700
Data Index: 2383791 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4528. Min Act: -0.1700
Data Index: 4502885 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4528. Min Act: -0.1700
Data Index: 4173688 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4216. Min Act: -0.1700
Data Index: 44610 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4216. Min Act: -0.1700
Data Index: 6028801 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.4216. Min Act: -0.1700
Data Index: 7091333 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3903. Min Act: -0.1700
Data Index: 1117203 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3903. Min Act: -0.1700
Data Index: 4606648 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3591. Min Act: -0.1700
Data Index: 5153748 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3591. Min Act: -0.1700
Data Index: 4526335 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3591. Min Act: -0.1700
Data Index: 1234356 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.3278. Min Act: -0.1700
Data Index: 2816359 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.2966. Min Act: -0.1700
Data Index: 1925532 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8278. Min Range: -4.8278
Max Act: 4.2966. Min Act: -0.1700
Data Index: 2006833 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19