Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9928. Min Act: -0.1700
Data Index: 6640245 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9928. Min Act: -0.1700
Data Index: 194071 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.9616. Min Act: -0.1700
Data Index: 6922098 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.8991. Min Act: -0.1700
Data Index: 1795351 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.8366. Min Act: -0.1700
Data Index: 2894699 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7741. Min Act: -0.1700
Data Index: 1178846 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7741. Min Act: -0.1700
Data Index: 3937875 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 271728 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 5559042 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 1205208 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 2209610 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7428. Min Act: -0.1700
Data Index: 4087566 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7116. Min Act: -0.1700
Data Index: 5301469 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.7116. Min Act: -0.1700
Data Index: 2293964 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6491. Min Act: -0.1700
Data Index: 5779609 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6491. Min Act: -0.1700
Data Index: 6034889 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6178. Min Act: -0.1700
Data Index: 3468191 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.6178. Min Act: -0.1700
Data Index: 2214354 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5866. Min Act: -0.1700
Data Index: 5020464 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9928. Min Range: -5.9928
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1526836 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19