Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1563. Min Range: -8.1563
Max Act: 8.1563. Min Act: -0.1700
Data Index: 5033239 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1563. Min Range: -8.1563
Max Act: 8.1563. Min Act: -0.1700
Data Index: 8069635 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1563. Min Range: -8.1563
Max Act: 8.0313. Min Act: -0.1700
Data Index: 4637733 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.9375. Min Act: -0.1700
Data Index: 4094690 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.9688. Min Act: -0.1700
Data Index: 4807580 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.8438. Min Act: -0.1700
Data Index: 7849025 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.8750. Min Act: -0.1700
Data Index: 1858922 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.8125. Min Act: -0.1700
Data Index: 568649 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.7500. Min Act: -0.1700
Data Index: 6960024 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.7188. Min Act: -0.1700
Data Index: 3561662 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.6875. Min Act: -0.1700
Data Index: 8682717 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.6563. Min Act: -0.1700
Data Index: 4714006 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.6250. Min Act: -0.1700
Data Index: 7257471 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5938. Min Act: -0.1700
Data Index: 3183647 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5625. Min Act: -0.1700
Data Index: 3933150 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5625. Min Act: -0.1700
Data Index: 7217076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5481966 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5313. Min Act: -0.1700
Data Index: 1340899 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.5000. Min Act: -0.1700
Data Index: 2336902 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1563. Min Range: -8.1563
Max Act: 7.4688. Min Act: -0.1700
Data Index: 109125 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19