Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6171 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0374. Min Act: -0.1700
Data Index: 496636 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 6815578 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 3189853 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.6937. Min Act: -0.1700
Data Index: 2748724 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5999. Min Act: -0.1700
Data Index: 2739031 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5687. Min Act: -0.1700
Data Index: 3800612 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5687. Min Act: -0.1700
Data Index: 4639952 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5687. Min Act: -0.1700
Data Index: 210859 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2006466 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5062. Min Act: -0.1700
Data Index: 2734793 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5062. Min Act: -0.1700
Data Index: 1650817 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5062. Min Act: -0.1700
Data Index: 976456 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5062. Min Act: -0.1700
Data Index: 8104433 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5062. Min Act: -0.1700
Data Index: 2776167 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.5374. Min Act: -0.1700
Data Index: 4595476 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.4749. Min Act: -0.1700
Data Index: 6434079 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.4749. Min Act: -0.1700
Data Index: 2479093 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.4749. Min Act: -0.1700
Data Index: 7931859 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.4437. Min Act: -0.1700
Data Index: 6214587 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.4437. Min Act: -0.1700
Data Index: 6165777 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19