Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.8686. Min Act: -0.1700
Data Index: 3349206 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.3374. Min Act: -0.1700
Data Index: 8351501 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.2124. Min Act: -0.1700
Data Index: 6968047 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.1811. Min Act: -0.1700
Data Index: 3066726 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0561. Min Act: -0.1700
Data Index: 1440226 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0561. Min Act: -0.1700
Data Index: 221290 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0874. Min Act: -0.1700
Data Index: 4179431 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0874. Min Act: -0.1700
Data Index: 3406956 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0561. Min Act: -0.1700
Data Index: 116716 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8686. Min Range: -7.8686
Max Act: 7.0249. Min Act: -0.1700
Data Index: 2714109 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.9311. Min Act: -0.1700
Data Index: 1149270 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.9311. Min Act: -0.1700
Data Index: 8353808 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 6749513 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8686. Min Act: -0.1700
Data Index: 310766 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8686. Min Act: -0.1700
Data Index: 4645760 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8686. Min Act: -0.1700
Data Index: 5014702 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 5621505 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8374. Min Act: -0.1700
Data Index: 8793579 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8374. Min Act: -0.1700
Data Index: 3541239 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8686. Min Range: -7.8686
Max Act: 6.8374. Min Act: -0.1700
Data Index: 6692508 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19