Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.8417. Min Act: -0.1700
Data Index: 8220886 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.7480. Min Act: -0.1700
Data Index: 75336 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.7167. Min Act: -0.1700
Data Index: 6299581 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.7480. Min Act: -0.1700
Data Index: 4042847 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.7167. Min Act: -0.1700
Data Index: 6122903 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6855. Min Act: -0.1700
Data Index: 8220883 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 4673573 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 3825364 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 8220884 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 1178920 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 6478274 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6542. Min Act: -0.1700
Data Index: 4115213 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 5665733 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 8181324 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 5449837 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 7692131 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 1938321 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 5361532 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.6230. Min Act: -0.1700
Data Index: 1396489 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8417. Min Range: -4.8417
Max Act: 4.5917. Min Act: -0.1700
Data Index: 4972517 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19