Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.7158. Min Act: -0.1700
Data Index: 5136192 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.6221. Min Act: -0.1700
Data Index: 7551235 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.5283. Min Act: -0.1700
Data Index: 5030805 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.4971. Min Act: -0.1700
Data Index: 582577 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.4346. Min Act: -0.1700
Data Index: 8205827 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.4033. Min Act: -0.1700
Data Index: 8755823 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.3096. Min Act: -0.1700
Data Index: 6683858 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.3096. Min Act: -0.1700
Data Index: 3676296 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.3408. Min Act: -0.1700
Data Index: 5164566 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2783. Min Act: -0.1700
Data Index: 6320920 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.3096. Min Act: -0.1700
Data Index: 5145078 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2471. Min Act: -0.1700
Data Index: 5096936 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2471. Min Act: -0.1700
Data Index: 56369 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2158. Min Act: -0.1700
Data Index: 3646218 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2471. Min Act: -0.1700
Data Index: 847343 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.1846. Min Act: -0.1700
Data Index: 3351534 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2471. Min Act: -0.1700
Data Index: 6055855 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2158. Min Act: -0.1700
Data Index: 7906421 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.2158. Min Act: -0.1700
Data Index: 4839509 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7158. Min Range: -6.7158
Max Act: 6.1533. Min Act: -0.1700
Data Index: 8205255 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19