Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.5381. Min Act: -0.1700
Data Index: 2045939 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.5224. Min Act: -0.1700
Data Index: 5796078 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.4441. Min Act: -0.1700
Data Index: 4654197 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.4284. Min Act: -0.1700
Data Index: 7124034 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3657. Min Act: -0.1700
Data Index: 347728 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3500. Min Act: -0.1700
Data Index: 5832971 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3500. Min Act: -0.1700
Data Index: 8742207 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3343. Min Act: -0.1700
Data Index: 786426 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3030. Min Act: -0.1700
Data Index: 6221772 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.3030. Min Act: -0.1700
Data Index: 3178039 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2716. Min Act: -0.1700
Data Index: 7280015 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2558. Min Act: -0.1700
Data Index: 1668318 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2558. Min Act: -0.1700
Data Index: 8297408 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2401. Min Act: -0.1700
Data Index: 3693281 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2244. Min Act: -0.1700
Data Index: 6048263 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2087. Min Act: -0.1700
Data Index: 5697141 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2087. Min Act: -0.1700
Data Index: 2751720 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2087. Min Act: -0.1700
Data Index: 1585742 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2087. Min Act: -0.1700
Data Index: 5041817 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5381. Min Range: -3.5381
Max Act: 3.2087. Min Act: -0.1700
Data Index: 5558443 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19