Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2085. Min Range: -5.2085
Max Act: 5.2085. Min Act: -0.1700
Data Index: 6285354 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2085. Min Range: -5.2085
Max Act: 5.1460. Min Act: -0.1700
Data Index: 1942480 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2085. Min Range: -5.2085
Max Act: 5.1773. Min Act: -0.1700
Data Index: 3575839 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2085. Min Range: -5.2085
Max Act: 5.0835. Min Act: -0.1700
Data Index: 1917706 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2085. Min Range: -5.2085
Max Act: 5.0835. Min Act: -0.1700
Data Index: 326000 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.9273. Min Act: -0.1700
Data Index: 2275883 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.9273. Min Act: -0.1700
Data Index: 3058564 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.9273. Min Act: -0.1700
Data Index: 325993 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8648. Min Act: -0.1700
Data Index: 1510169 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8648. Min Act: -0.1700
Data Index: 5898415 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8335. Min Act: -0.1700
Data Index: 8223660 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8335. Min Act: -0.1700
Data Index: 6497371 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8023. Min Act: -0.1700
Data Index: 325997 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8023. Min Act: -0.1700
Data Index: 4410903 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8023. Min Act: -0.1700
Data Index: 211774 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8023. Min Act: -0.1700
Data Index: 8277517 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.7710. Min Act: -0.1700
Data Index: 325998 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.8023. Min Act: -0.1700
Data Index: 5048846 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.7710. Min Act: -0.1700
Data Index: 1752412 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2085. Min Range: -5.2085
Max Act: 4.7710. Min Act: -0.1700
Data Index: 234966 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19