Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.7776. Min Act: -0.1700
Data Index: 2461355 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6770745 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.7464. Min Act: -0.1700
Data Index: 19209 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.7151. Min Act: -0.1700
Data Index: 1805847 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.7151. Min Act: -0.1700
Data Index: 1815590 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6526. Min Act: -0.1700
Data Index: 1295729 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6839. Min Act: -0.1700
Data Index: 8476105 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6839. Min Act: -0.1700
Data Index: 1564752 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6214. Min Act: -0.1700
Data Index: 93978 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6526. Min Act: -0.1700
Data Index: 5856922 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6839. Min Act: -0.1700
Data Index: 2379843 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.6214. Min Act: -0.1700
Data Index: 4757215 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5644886 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5901. Min Act: -0.1700
Data Index: 6040376 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5995494 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5536507 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5589. Min Act: -0.1700
Data Index: 8334264 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5901. Min Act: -0.1700
Data Index: 6885081 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5589. Min Act: -0.1700
Data Index: 689238 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7776. Min Range: -4.7776
Max Act: 4.5589. Min Act: -0.1700
Data Index: 2952242 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19