Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6025 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.2252. Min Act: -0.1700
Data Index: 8470263 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.2252. Min Act: -0.1700
Data Index: 1495781 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.1627. Min Act: -0.1700
Data Index: 7332822 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.0377. Min Act: -0.1700
Data Index: 4277917 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.0377. Min Act: -0.1700
Data Index: 295314 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2252. Min Range: -8.2252
Max Act: 8.0377. Min Act: -0.1700
Data Index: 76334 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.9127. Min Act: -0.1700
Data Index: 481646 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.9127. Min Act: -0.1700
Data Index: 1683894 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.9127. Min Act: -0.1700
Data Index: 3291192 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.9127. Min Act: -0.1700
Data Index: 3672341 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.9127. Min Act: -0.1700
Data Index: 2474999 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.8502. Min Act: -0.1700
Data Index: 4007490 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.8502. Min Act: -0.1700
Data Index: 7735398 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 600443 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.8502. Min Act: -0.1700
Data Index: 3164425 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 1958556 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 545523 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 3542698 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 3469885 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2252. Min Range: -8.2252
Max Act: 7.7877. Min Act: -0.1700
Data Index: 5724956 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19