Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3113. Min Range: -8.3113
Max Act: 8.3113. Min Act: -0.1700
Data Index: 7212829 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3113. Min Range: -8.3113
Max Act: 8.1863. Min Act: -0.1700
Data Index: 2693714 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3113. Min Range: -8.3113
Max Act: 8.0613. Min Act: -0.1700
Data Index: 6560635 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3113. Min Range: -8.3113
Max Act: 8.0613. Min Act: -0.1700
Data Index: 5521050 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.9363. Min Act: -0.1700
Data Index: 6281681 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.9363. Min Act: -0.1700
Data Index: 7412875 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.9363. Min Act: -0.1700
Data Index: 3240670 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.9363. Min Act: -0.1700
Data Index: 6663410 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.8738. Min Act: -0.1700
Data Index: 2146012 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.8738. Min Act: -0.1700
Data Index: 5386151 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.8738. Min Act: -0.1700
Data Index: 7986636 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.8738. Min Act: -0.1700
Data Index: 266795 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.8113. Min Act: -0.1700
Data Index: 5889768 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.7488. Min Act: -0.1700
Data Index: 6599888 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.7488. Min Act: -0.1700
Data Index: 7927677 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 2660903 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 4604451 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 751655 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 5759703 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3113. Min Range: -8.3113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 5665769 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19