Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.3826. Min Act: -0.1700
Data Index: 2284062 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.2889. Min Act: -0.1700
Data Index: 2231332 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1951. Min Act: -0.1700
Data Index: 2475574 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1639. Min Act: -0.1700
Data Index: 326624 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1639. Min Act: -0.1700
Data Index: 7734407 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1326. Min Act: -0.1700
Data Index: 5315304 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1326. Min Act: -0.1700
Data Index: 3172485 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1014. Min Act: -0.1700
Data Index: 4530682 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1014. Min Act: -0.1700
Data Index: 8767875 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1014. Min Act: -0.1700
Data Index: 4330869 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1014. Min Act: -0.1700
Data Index: 1244341 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0701. Min Act: -0.1700
Data Index: 4718196 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0389. Min Act: -0.1700
Data Index: 3437138 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0701. Min Act: -0.1700
Data Index: 381199 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6146540 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0076. Min Act: -0.1700
Data Index: 364203 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0076. Min Act: -0.1700
Data Index: 1245380 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4020404 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.0076. Min Act: -0.1700
Data Index: 340305 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.9139. Min Act: -0.1700
Data Index: 7495649 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19