Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.3635. Min Act: -0.1700
Data Index: 3127787 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.1760. Min Act: -0.1700
Data Index: 3781165 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.1135. Min Act: -0.1700
Data Index: 1870970 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.0510. Min Act: -0.1700
Data Index: 5286234 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.0510. Min Act: -0.1700
Data Index: 5067501 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3635. Min Range: -9.3635
Max Act: 9.1135. Min Act: -0.1700
Data Index: 3322938 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.9885. Min Act: -0.1700
Data Index: 3720246 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.9885. Min Act: -0.1700
Data Index: 6850883 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.9885. Min Act: -0.1700
Data Index: 2855391 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.8635. Min Act: -0.1700
Data Index: 2652501 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.8010. Min Act: -0.1700
Data Index: 4113630 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.8010. Min Act: -0.1700
Data Index: 4142002 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.7385. Min Act: -0.1700
Data Index: 3064792 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.7385. Min Act: -0.1700
Data Index: 3096663 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6760. Min Act: -0.1700
Data Index: 7209684 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6760. Min Act: -0.1700
Data Index: 7209683 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6135. Min Act: -0.1700
Data Index: 3913379 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6135. Min Act: -0.1700
Data Index: 4368148 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6135. Min Act: -0.1700
Data Index: 6299559 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3635. Min Range: -9.3635
Max Act: 8.6135. Min Act: -0.1700
Data Index: 3913372 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19