Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0478. Min Range: -5.0478
Max Act: 5.0478. Min Act: -0.1700
Data Index: 7891538 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6203479 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6012243 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 7217857 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6589444 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4012748 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4484867 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7978. Min Act: -0.1700
Data Index: 437435 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7978. Min Act: -0.1700
Data Index: 6149896 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 3726937 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7665. Min Act: -0.1700
Data Index: 613747 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7665. Min Act: -0.1700
Data Index: 8380229 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 5714865 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7040. Min Act: -0.1700
Data Index: 7777946 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7665. Min Act: -0.1700
Data Index: 3832079 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 3726939 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 8126733 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 4431490 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6728. Min Act: -0.1700
Data Index: 3219372 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.6103. Min Act: -0.1700
Data Index: 6117513 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19