Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 584 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.8626. Min Act: -0.1700
Data Index: 334482 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.8626. Min Act: -0.1700
Data Index: 3602752 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 7269153 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.8001. Min Act: -0.1700
Data Index: 1917556 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.7688. Min Act: -0.1700
Data Index: 563001 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.6751. Min Act: -0.1700
Data Index: 4637750 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.6751. Min Act: -0.1700
Data Index: 8738014 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.6438. Min Act: -0.1700
Data Index: 5434611 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.6438. Min Act: -0.1700
Data Index: 5609351 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5501. Min Act: -0.1700
Data Index: 2810610 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5501. Min Act: -0.1700
Data Index: 4530659 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5501. Min Act: -0.1700
Data Index: 4001826 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7800802 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5501. Min Act: -0.1700
Data Index: 8207858 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5188. Min Act: -0.1700
Data Index: 1979887 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5188. Min Act: -0.1700
Data Index: 367713 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5188. Min Act: -0.1700
Data Index: 1945831 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.4876. Min Act: -0.1700
Data Index: 4203662 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.5188. Min Act: -0.1700
Data Index: 2499704 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8626. Min Range: -6.8626
Max Act: 6.4876. Min Act: -0.1700
Data Index: 5055378 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19