Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4367. Min Range: -8.4367
Max Act: 8.4367. Min Act: -0.1700
Data Index: 8022005 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4367. Min Range: -8.4367
Max Act: 8.3117. Min Act: -0.1700
Data Index: 7193843 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4367. Min Range: -8.4367
Max Act: 8.1867. Min Act: -0.1700
Data Index: 1723669 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.9992. Min Act: -0.1700
Data Index: 2978880 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8742. Min Act: -0.1700
Data Index: 5265234 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8742. Min Act: -0.1700
Data Index: 3929385 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8117. Min Act: -0.1700
Data Index: 1342626 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8117. Min Act: -0.1700
Data Index: 3587024 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8117. Min Act: -0.1700
Data Index: 1612138 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.8117. Min Act: -0.1700
Data Index: 2611835 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 6779552 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6867. Min Act: -0.1700
Data Index: 933187 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 4466970 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 1737688 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 2374239 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 8449806 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 6223862 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.5617. Min Act: -0.1700
Data Index: 4515043 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.5617. Min Act: -0.1700
Data Index: 5742906 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4367. Min Range: -8.4367
Max Act: 7.6242. Min Act: -0.1700
Data Index: 6300061 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19