Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1698 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.2982. Min Act: -0.1700
Data Index: 5883765 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.2357. Min Act: -0.1700
Data Index: 5234515 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.2357. Min Act: -0.1700
Data Index: 1279948 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.2357. Min Act: -0.1700
Data Index: 3610012 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.2357. Min Act: -0.1700
Data Index: 5814276 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.1107. Min Act: -0.1700
Data Index: 5348208 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.1107. Min Act: -0.1700
Data Index: 4835608 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2982. Min Range: -9.2982
Max Act: 9.0482. Min Act: -0.1700
Data Index: 2082522 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9232. Min Act: -0.1700
Data Index: 1017806 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9857. Min Act: -0.1700
Data Index: 276435 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9232. Min Act: -0.1700
Data Index: 7333005 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9232. Min Act: -0.1700
Data Index: 4039709 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9232. Min Act: -0.1700
Data Index: 233744 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.9232. Min Act: -0.1700
Data Index: 4160848 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.8607. Min Act: -0.1700
Data Index: 5976287 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.8607. Min Act: -0.1700
Data Index: 2211398 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.8607. Min Act: -0.1700
Data Index: 7135871 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.7982. Min Act: -0.1700
Data Index: 3241450 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.6732. Min Act: -0.1700
Data Index: 4816668 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2982. Min Range: -9.2982
Max Act: 8.7357. Min Act: -0.1700
Data Index: 4426927 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19