Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4278 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1006. Min Range: -5.1006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 6174139 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3609809 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.9444. Min Act: -0.1700
Data Index: 4552411 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.9131. Min Act: -0.1700
Data Index: 5983577 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.9131. Min Act: -0.1700
Data Index: 2773595 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8506. Min Act: -0.1700
Data Index: 4035432 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8194. Min Act: -0.1700
Data Index: 6951888 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7881. Min Act: -0.1700
Data Index: 470214 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8194. Min Act: -0.1700
Data Index: 7154576 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8194. Min Act: -0.1700
Data Index: 4257586 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8194. Min Act: -0.1700
Data Index: 5020429 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.8194. Min Act: -0.1700
Data Index: 529731 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7881. Min Act: -0.1700
Data Index: 4632168 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7881. Min Act: -0.1700
Data Index: 2201770 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7881. Min Act: -0.1700
Data Index: 1440858 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7569. Min Act: -0.1700
Data Index: 1945456 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7256. Min Act: -0.1700
Data Index: 8155728 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7569. Min Act: -0.1700
Data Index: 4029793 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7569. Min Act: -0.1700
Data Index: 1268933 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1006. Min Range: -5.1006
Max Act: 4.7569. Min Act: -0.1700
Data Index: 250998 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19