Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9782. Min Act: -0.1700
Data Index: 2252105 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9782. Min Act: -0.1700
Data Index: 4263040 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9609. Min Act: -0.1700
Data Index: 650347 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9523. Min Act: -0.1700
Data Index: 260742 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9523. Min Act: -0.1700
Data Index: 4128924 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9351. Min Act: -0.1700
Data Index: 8441701 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9351. Min Act: -0.1699
Data Index: 6050739 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9265. Min Act: -0.1700
Data Index: 7490318 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9179. Min Act: -0.1700
Data Index: 1532609 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9179. Min Act: -0.1700
Data Index: 6672807 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9179. Min Act: -0.1700
Data Index: 5256041 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9265. Min Act: -0.1700
Data Index: 2898486 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9179. Min Act: -0.1700
Data Index: 4412566 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9093. Min Act: -0.1700
Data Index: 1714468 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9093. Min Act: -0.1700
Data Index: 7939492 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9007. Min Act: -0.1700
Data Index: 4202738 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9093. Min Act: -0.1700
Data Index: 234526 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9007. Min Act: -0.1700
Data Index: 7703679 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.8922. Min Act: -0.1700
Data Index: 5251794 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9782. Min Range: -0.9782
Max Act: 0.9007. Min Act: -0.1700
Data Index: 6509413 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19