Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5242. Min Range: -8.5242
Max Act: 8.5242. Min Act: -0.1700
Data Index: 2363303 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.7117. Min Act: -0.1700
Data Index: 4699807 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6735470 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 751758 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 512925 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 1239574 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 1368208 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 7438134 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 436183 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 810695 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.5242. Min Act: -0.1700
Data Index: 8810354 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.4617. Min Act: -0.1700
Data Index: 614850 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.4617. Min Act: -0.1700
Data Index: 8541343 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3680. Min Act: -0.1700
Data Index: 4117931 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3680. Min Act: -0.1700
Data Index: 1488808 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3055. Min Act: -0.1700
Data Index: 2910123 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3680. Min Act: -0.1700
Data Index: 2143014 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3055. Min Act: -0.1700
Data Index: 7167595 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3055. Min Act: -0.1700
Data Index: 1488804 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5242. Min Range: -8.5242
Max Act: 7.3055. Min Act: -0.1700
Data Index: 4923466 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19