Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1731. Min Range: -8.1731
Max Act: 8.1731. Min Act: -0.1700
Data Index: 86660 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.8919. Min Act: -0.1700
Data Index: 2160281 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.6419. Min Act: -0.1700
Data Index: 3804327 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.5794. Min Act: -0.1700
Data Index: 2608146 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.6106. Min Act: -0.1700
Data Index: 3774964 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.5481. Min Act: -0.1700
Data Index: 363720 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.4544. Min Act: -0.1700
Data Index: 7688584 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.4231. Min Act: -0.1700
Data Index: 601319 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.4231. Min Act: -0.1700
Data Index: 1851818 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.4231. Min Act: -0.1700
Data Index: 2940246 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3606. Min Act: -0.1700
Data Index: 1394847 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3919. Min Act: -0.1700
Data Index: 4334234 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3294. Min Act: -0.1700
Data Index: 1070239 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3919. Min Act: -0.1700
Data Index: 5412323 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3606. Min Act: -0.1700
Data Index: 3149167 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3294. Min Act: -0.1700
Data Index: 1386426 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.3294. Min Act: -0.1700
Data Index: 2523723 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.2356. Min Act: -0.1700
Data Index: 1165553 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.2356. Min Act: -0.1700
Data Index: 6924549 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1731. Min Range: -8.1731
Max Act: 7.2356. Min Act: -0.1700
Data Index: 4908328 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19