Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0087. Min Range: -5.0087
Max Act: 5.0087. Min Act: -0.1700
Data Index: 105227 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.8525. Min Act: -0.1700
Data Index: 5301762 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7284727 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7994573 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7900. Min Act: -0.1700
Data Index: 105225 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7900. Min Act: -0.1700
Data Index: 5779386 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7900. Min Act: -0.1700
Data Index: 485778 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7587. Min Act: -0.1700
Data Index: 4487581 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7587. Min Act: -0.1700
Data Index: 3142450 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7587. Min Act: -0.1700
Data Index: 7446365 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.7275. Min Act: -0.1700
Data Index: 1641801 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6962. Min Act: -0.1699
Data Index: 8086835 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6962. Min Act: -0.1700
Data Index: 105222 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6962. Min Act: -0.1700
Data Index: 3970238 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6962. Min Act: -0.1700
Data Index: 3705351 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6962. Min Act: -0.1700
Data Index: 6213812 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6650. Min Act: -0.1700
Data Index: 929490 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6650. Min Act: -0.1700
Data Index: 1120576 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6650. Min Act: -0.1700
Data Index: 782009 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0087. Min Range: -5.0087
Max Act: 4.6650. Min Act: -0.1700
Data Index: 6131926 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19