Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4318. Min Range: -4.4318
Max Act: 4.4318. Min Act: -0.1700
Data Index: 3337445 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9943. Min Act: -0.1700
Data Index: 4433663 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5556340 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9943. Min Act: -0.1700
Data Index: 2502167 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9943. Min Act: -0.1700
Data Index: 1625698 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9630. Min Act: -0.1700
Data Index: 7006990 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9630. Min Act: -0.1700
Data Index: 6568820 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9317. Min Act: -0.1700
Data Index: 7535932 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9317. Min Act: -0.1700
Data Index: 820979 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9005. Min Act: -0.1700
Data Index: 3341897 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9317. Min Act: -0.1700
Data Index: 5927814 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.9005. Min Act: -0.1700
Data Index: 6398979 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8692. Min Act: -0.1700
Data Index: 3638416 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8692. Min Act: -0.1700
Data Index: 4498255 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8223. Min Act: -0.1700
Data Index: 4700576 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8067. Min Act: -0.1700
Data Index: 1404272 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8067. Min Act: -0.1700
Data Index: 6313888 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8067. Min Act: -0.1700
Data Index: 6883829 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8067. Min Act: -0.1700
Data Index: 2246612 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4318. Min Range: -4.4318
Max Act: 3.8067. Min Act: -0.1700
Data Index: 1145489 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19