Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1300 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.7260. Min Act: -0.1700
Data Index: 8453510 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.6010. Min Act: -0.1700
Data Index: 8639291 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.5385. Min Act: -0.1700
Data Index: 4655228 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.4760. Min Act: -0.1700
Data Index: 8741946 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.4135. Min Act: -0.1700
Data Index: 2682705 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.4135. Min Act: -0.1700
Data Index: 766045 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.2885. Min Act: -0.1700
Data Index: 6359857 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.2260. Min Act: -0.1700
Data Index: 4723651 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.2260. Min Act: -0.1700
Data Index: 3844647 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.1635. Min Act: -0.1700
Data Index: 486246 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.1010. Min Act: -0.1700
Data Index: 6141349 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.0385. Min Act: -0.1700
Data Index: 2630517 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.0385. Min Act: -0.1700
Data Index: 4690832 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7260. Min Range: -9.7260
Max Act: 8.9760. Min Act: -0.1700
Data Index: 2727893 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.0385. Min Act: -0.1700
Data Index: 5589961 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.0385. Min Act: -0.1700
Data Index: 8315868 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7260. Min Range: -9.7260
Max Act: 9.0385. Min Act: -0.1700
Data Index: 8279638 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7260. Min Range: -9.7260
Max Act: 8.9760. Min Act: -0.1700
Data Index: 478917 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7260. Min Range: -9.7260
Max Act: 8.9760. Min Act: -0.1700
Data Index: 6979725 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7260. Min Range: -9.7260
Max Act: 8.9135. Min Act: -0.1700
Data Index: 2102344 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19