Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6014 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3889. Min Range: -8.3889
Max Act: 8.3889. Min Act: -0.1700
Data Index: 1115914 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3889. Min Range: -8.3889
Max Act: 8.1702. Min Act: -0.1700
Data Index: 1115913 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3889. Min Range: -8.3889
Max Act: 8.0139. Min Act: -0.1700
Data Index: 1115920 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.7952. Min Act: -0.1700
Data Index: 1115927 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.6702. Min Act: -0.1700
Data Index: 1115925 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.7014. Min Act: -0.1700
Data Index: 1115915 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.6077. Min Act: -0.1700
Data Index: 5660787 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.5764. Min Act: -0.1700
Data Index: 1115923 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.5139. Min Act: -0.1700
Data Index: 1115919 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.3577. Min Act: -0.1700
Data Index: 1115912 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.3264. Min Act: -0.1700
Data Index: 6762549 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.2639. Min Act: -0.1700
Data Index: 1115926 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.1077. Min Act: -0.1700
Data Index: 1115924 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.1077. Min Act: -0.1700
Data Index: 1115931 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.0764. Min Act: -0.1700
Data Index: 6013282 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.0452. Min Act: -0.1700
Data Index: 1115918 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.0139. Min Act: -0.1700
Data Index: 5779983 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3889. Min Range: -8.3889
Max Act: 7.0452. Min Act: -0.1700
Data Index: 4045606 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3889. Min Range: -8.3889
Max Act: 6.9202. Min Act: -0.1700
Data Index: 1115930 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3889. Min Range: -8.3889
Max Act: 6.8889. Min Act: -0.1700
Data Index: 6658797 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19