Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0077. Min Range: -8.0077
Max Act: 8.0077. Min Act: -0.1700
Data Index: 405610 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.9452. Min Act: -0.1700
Data Index: 352621 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.9452. Min Act: -0.1700
Data Index: 6946424 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.9452. Min Act: -0.1700
Data Index: 5854093 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.9452. Min Act: -0.1700
Data Index: 2244855 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.8827. Min Act: -0.1700
Data Index: 2810750 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.8827. Min Act: -0.1700
Data Index: 215859 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.8827. Min Act: -0.1700
Data Index: 4812212 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.7577. Min Act: -0.1700
Data Index: 2210110 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.7577. Min Act: -0.1700
Data Index: 1423694 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.7577. Min Act: -0.1700
Data Index: 5243249 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.7577. Min Act: -0.1700
Data Index: 1411235 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 8374263 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 4272316 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 1877877 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 540055 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 1392290 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 67923 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 5590806 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0077. Min Range: -8.0077
Max Act: 7.6014. Min Act: -0.1700
Data Index: 3025545 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19