Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.4767. Min Act: -0.1700
Data Index: 622668 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.4454. Min Act: -0.1700
Data Index: 3886323 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.3517. Min Act: -0.1700
Data Index: 6065091 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.3204. Min Act: -0.1700
Data Index: 6543031 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.2267. Min Act: -0.1700
Data Index: 3964928 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.2267. Min Act: -0.1700
Data Index: 4697034 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.1017. Min Act: -0.1700
Data Index: 3886324 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.1017. Min Act: -0.1700
Data Index: 598314 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.0704. Min Act: -0.1700
Data Index: 5675865 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.0079. Min Act: -0.1700
Data Index: 3964927 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4767. Min Range: -7.4767
Max Act: 7.0392. Min Act: -0.1700
Data Index: 4187263 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.9454. Min Act: -0.1700
Data Index: 5217538 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.9142. Min Act: -0.1700
Data Index: 176142 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.9454. Min Act: -0.1700
Data Index: 4827208 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.9142. Min Act: -0.1700
Data Index: 6839529 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.8829. Min Act: -0.1700
Data Index: 7608500 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.8829. Min Act: -0.1700
Data Index: 4976354 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.8829. Min Act: -0.1700
Data Index: 5494490 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.8517. Min Act: -0.1700
Data Index: 2603706 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4767. Min Range: -7.4767
Max Act: 6.8829. Min Act: -0.1700
Data Index: 1779809 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19