Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.5875. Min Act: -0.1700
Data Index: 6217309 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.6187. Min Act: -0.1700
Data Index: 7354699 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.5875. Min Act: -0.1700
Data Index: 4794471 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.5250. Min Act: -0.1700
Data Index: 4794472 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.5562. Min Act: -0.1700
Data Index: 1193446 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4937. Min Act: -0.1700
Data Index: 1372965 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.5562. Min Act: -0.1700
Data Index: 7196889 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4937. Min Act: -0.1700
Data Index: 3984717 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4937. Min Act: -0.1700
Data Index: 1392707 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4937. Min Act: -0.1700
Data Index: 8767321 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1945887 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4312. Min Act: -0.1700
Data Index: 6858294 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4625. Min Act: -0.1700
Data Index: 8802054 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4625. Min Act: -0.1700
Data Index: 5355439 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4625. Min Act: -0.1700
Data Index: 5644859 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4312. Min Act: -0.1700
Data Index: 3730251 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4312. Min Act: -0.1700
Data Index: 1571617 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4312. Min Act: -0.1700
Data Index: 1285110 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4000. Min Act: -0.1700
Data Index: 1651771 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6187. Min Range: -5.6187
Max Act: 5.4000. Min Act: -0.1700
Data Index: 7402696 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19