Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5237 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9294. Min Range: -8.9294
Max Act: 8.9294. Min Act: -0.1700
Data Index: 7700669 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9294. Min Range: -8.9294
Max Act: 8.2419. Min Act: -0.1700
Data Index: 3167243 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9294. Min Range: -8.9294
Max Act: 8.1794. Min Act: -0.1700
Data Index: 4881522 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.9919. Min Act: -0.1700
Data Index: 8809326 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.9294. Min Act: -0.1700
Data Index: 4172241 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.9294. Min Act: -0.1700
Data Index: 4822057 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.8669. Min Act: -0.1700
Data Index: 7003138 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.8669. Min Act: -0.1700
Data Index: 7127683 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.8044. Min Act: -0.1700
Data Index: 3412380 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.8044. Min Act: -0.1700
Data Index: 944170 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.8044. Min Act: -0.1700
Data Index: 3906393 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.7419. Min Act: -0.1700
Data Index: 3781386 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.7419. Min Act: -0.1700
Data Index: 4617300 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.7419. Min Act: -0.1700
Data Index: 4585032 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.7419. Min Act: -0.1700
Data Index: 1206195 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.7419. Min Act: -0.1700
Data Index: 3976611 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.6794. Min Act: -0.1700
Data Index: 4213921 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.6794. Min Act: -0.1700
Data Index: 3255652 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.6794. Min Act: -0.1700
Data Index: 6768790 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9294. Min Range: -8.9294
Max Act: 7.6794. Min Act: -0.1700
Data Index: 3075164 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19