Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.4754. Min Act: -0.1700
Data Index: 1765970 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.4129. Min Act: -0.1700
Data Index: 4349783 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.2879. Min Act: -0.1700
Data Index: 6975633 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.2254. Min Act: -0.1700
Data Index: 6230636 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.2254. Min Act: -0.1700
Data Index: 5351393 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1628. Min Act: -0.1700
Data Index: 4816150 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1941. Min Act: -0.1700
Data Index: 6797867 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 4578034 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 7316391 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1316. Min Act: -0.1700
Data Index: 4926107 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 4969877 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 5271795 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 5242079 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 1938787 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.1003. Min Act: -0.1700
Data Index: 27349 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.0691. Min Act: -0.1700
Data Index: 598815 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.0691. Min Act: -0.1700
Data Index: 5712667 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.0691. Min Act: -0.1700
Data Index: 7852410 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.0378. Min Act: -0.1700
Data Index: 1893143 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4754. Min Range: -4.4754
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4312660 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19