Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1277 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0194. Min Range: -9.0194
Max Act: 9.0194. Min Act: -0.1700
Data Index: 5603182 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.7069. Min Act: -0.1700
Data Index: 2233315 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.7069. Min Act: -0.1700
Data Index: 6594585 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.7069. Min Act: -0.1700
Data Index: 5717269 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.6444. Min Act: -0.1700
Data Index: 1528474 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.6444. Min Act: -0.1700
Data Index: 1813674 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.6444. Min Act: -0.1700
Data Index: 1740440 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.6444. Min Act: -0.1700
Data Index: 8756924 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.6444. Min Act: -0.1700
Data Index: 8827960 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 8242404 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5819. Min Act: -0.1700
Data Index: 8427163 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5819. Min Act: -0.1700
Data Index: 5757862 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 7711594 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 3880913 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 2338321 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 5510212 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.3944. Min Act: -0.1700
Data Index: 7835694 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.4569. Min Act: -0.1700
Data Index: 2927211 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.4569. Min Act: -0.1700
Data Index: 2445142 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0194. Min Range: -9.0194
Max Act: 8.4569. Min Act: -0.1700
Data Index: 6026319 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19