Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7596. Min Act: -0.1700
Data Index: 565460 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6346. Min Act: -0.1700
Data Index: 3633962 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6346. Min Act: -0.1700
Data Index: 5650928 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.5721. Min Act: -0.1700
Data Index: 7189738 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.4471. Min Act: -0.1700
Data Index: 2960063 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.4471. Min Act: -0.1700
Data Index: 1975626 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.4158. Min Act: -0.1700
Data Index: 545513 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.4158. Min Act: -0.1700
Data Index: 5212716 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3846. Min Act: -0.1700
Data Index: 2019066 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.4158. Min Act: -0.1700
Data Index: 659840 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3846. Min Act: -0.1700
Data Index: 1384485 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3533. Min Act: -0.1700
Data Index: 4673905 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3533. Min Act: -0.1700
Data Index: 8529639 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3533. Min Act: -0.1700
Data Index: 3974906 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3533. Min Act: -0.1700
Data Index: 8251751 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3221. Min Act: -0.1700
Data Index: 4732316 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3221. Min Act: -0.1700
Data Index: 1775397 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.2908. Min Act: -0.1700
Data Index: 1132094 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.3221. Min Act: -0.1700
Data Index: 4725410 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.2908. Min Act: -0.1700
Data Index: 5740156 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19